htmlradar-mcp
Send your web page. See which part each person read.
npm · fingerprint db403fde47e036bf0b664bd1 · repository · RSS
16tools
5recorded versions
45dtracked
changed since 28 Oct
What changed
Changed between 28 October 2026 and 18 November 2026 (first seen 2026-11-18 15:54 UTC)
16 descriptions rewritten.
--- pinned/add_attachment +++ observed/add_attachment { "annotations": { "destructiveHint": false, - "description": "Attaches one file to a document already on HTMLRadar, for readers of its links to download. The file types are the website's (PDF, Office documents, images, CSV, text, Markdown, ZIP) and a document holds up to 20 files. The file travels as base64 in `content_base64`, because a tool argument is JSON, so it can be at most 5.0 MB, the same limit as publishing a page this way; a larger file (the website takes 25 MB) is added on the website. Readers see the file from the next time they load the page. There is no file-path argument: a file on disk reaches this tool only as content the caller has already read.", + "description": "Attaches one file to a document already on HTMLRadar, for readers of its links to download. The file types are the website's (PDF, Office documents, images, CSV, text, Markdown, ZIP) and a document holds up to 20 files. The file travels as base64 in `content_base64`, because a tool argument is JSON, so it can be at most 5.0 MB, the same limit as publishing a page this way; a larger file (the website takes 25 MB) is added on the website. Readers see the file from the next time they load the page. There is no file-path argument.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "The document — the document id from list_documents or list_shares.", + "description": "The document: the document id from list_documents or list_shares.", "type": "string" }, "filename": {
--- pinned/create_share +++ observed/create_share { "annotations": { "destructiveHint": false, - "description": "Creates an additional tracked link for a document already on HTMLRadar, with its own recipient label, gate, password, expiry and address. One link per recipient is what separates their reading reports. It uploads nothing and creates no second copy of the document, and it cannot publish new markup: it takes a document id, which list_shares returns and share_html returned when the document was first published. The link is live the moment it is returned. The answer includes the saved rules and comments state.", + "description": "Creates an additional tracked link for a document already on HTMLRadar, with its own recipient label, gate, password, expiry and address. One link per recipient is what separates their reading reports. It uploads nothing and creates no second copy of the document, and it cannot publish new markup. The document id comes from list_documents or list_shares. The link is live the moment it is returned, but a held or blocked document does not open for readers through any link. The answer includes the saved rules and whether comments are on.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "Only these exact addresses may open the link, e.g. [\"ravi@acme.com\"]. A separate list from the domains, and a visitor passes on either. Up to 500 addresses; past that a domain is the right tool. Needs the email gate, which is on by default; with it off the call is refused.", + "description": "Only these exact addresses may open the link. A separate list from the domains, and a visitor passes on either. Up to 500 addresses; an allowed domain covers all addresses in that domain. Needs the email gate, which is on by default; with it off the call is refused.", "items": { "type": "string" }, - "description": "The document to make another link for — the document id from list_shares, or the one share_html returned when the document was first published.", + "description": "The document to make another link for: the document id from list_documents or list_shares.", "type": "string" }, "expires_in_hours": { - "description": "Blocks save and print and adds a watermark; default true. Pass false for a document the recipient is meant to keep a copy of.", + "description": "Blocks save and print; default true. False allows a recipient to keep a copy.", "type": "boolean" }, "password": { - "description": "Who this link is for, e.g. \"Acme\". One link per recipient reads best.", + "description": "Who this link is for. A separate link for each recipient separates their reading reports.", "type": "string" }, "request_id": { - "description": "Leave unset on a first attempt. When a previous call failed saying it may still have been applied, pass the request_id that error named: the retry then returns the first result instead of doing it twice.", + "description": "Optional on a first attempt. When a previous call may have been applied, the request_id named by its error makes a retry return the first result instead of doing it twice.", "type": "string" }, "require_email": { - "description": "Ask the recipient for their email before the document opens. Defaults to true.", + "description": "Whether the recipient must give an email address before the document opens. Defaults to true.", "type": "boolean" }, + "show_watermark": { + "description": "Show a faint watermark when lock_deck is true. Defaults to true on creation; omitted on edit keeps the saved choice.", + "type": "boolean" + }, "slug": { "description": "Custom link name, so the URL reads /r/acme-proposal. Paid plans only.", "type": "string" - "description": "Verify that the address really is the reader's: we email a six-digit code and open the document only when the reader types it back. Off by default. Use it when the list of who opened the document has to be true rather than merely typed. Needs the email gate, which is on by default; with it off the call is refused.", + "description": "Whether the reader must prove their email address with a six-digit code before the document opens. Off by default. A verified address identifies the reader rather than an address merely typed into the gate. Needs the email gate, which is on by default; with it off the call is refused.", "type": "boolean" } },
--- pinned/get_document +++ observed/get_document { "annotations": { + "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "Read a document to change it" - "description": "Returns the current contents of a document on HTMLRadar so they can be changed and put back with replace_document. Each image embedded as a data URI appears as a short htmlradar-image reference instead of its data; keep references exactly as they are. A page over 5 MB of text even with its images as references is too large to read whole; with `query`, a word or phrase from the part to change, any page returns only the passages where that text appears, which replace_document `edits` can then change. It reads only this account's documents and changes nothing.", + "description": "Returns the current contents of a document on HTMLRadar so they can be changed and put back with replace_document. A change to a page already on HTMLRadar is made this way, for pages up to 30 MB, the same limit as the website: read the page here, then send the edited short form, or only the changes, to replace_document; a whole new file is needed only to replace the page itself. Each embedded PNG, JPEG, GIF and WebP image appears as a short htmlradar-image reference instead of its data; unchanged references restore the original images, and other embedded images, such as SVG, stay in the markup. Up to 5 MB of text and code, with its images as references, the whole page comes back. Between 5 MB and 20 MB it is too large to return whole: pass `query`, a word or phrase from the part to change, and it returns up to 20 passages where that text appears, exact text for `edits`. Over 20 MB of text and code besides its images, the page cannot be read or changed here. A document served from its own address has no stored contents to return. It reads only this account's documents and changes nothing.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "The document to read — the document id from list_documents or list_shares.", + "description": "The document to read: the document id from list_documents or list_shares.", "type": "string" }, "query": { - "description": "Text to find, 1 to 200 characters, matched literally with letter case ignored, such as a product name or a price. Returns up to 20 passages around the matches, and how many there are, instead of the whole page: the way to edit a page too large to read whole.", + "description": "Text to find, 1 to 200 characters, matched literally with letter case ignored, such as a product name or a price. Returns up to 20 passages around the matches, and how many there are, instead of the whole page. For a page too large to read whole, the passages provide exact text for edits.", "maxLength": 200, "minLength": 1, "type": "string"
--- pinned/get_page_guidelines +++ observed/get_page_guidelines { "annotations": { + "destructiveHint": false, "openWorldHint": false, "readOnlyHint": true, "title": "Get page guidelines" - "description": "Returns HTMLRadar's guidelines for pages that read well on phones and give accurate section reading", + "description": "Returns HTMLRadar's guidelines for pages that read well on phones and give accurate section reading times. It reads no account data and changes nothing.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {},
--- pinned/get_reading_records +++ observed/get_reading_records { "annotations": { + "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "Get a document's reading records" - "description": "Returns the reading records the HTMLRadar website exports as a spreadsheet, as CSV text: one row per section per read, with the link's label and address, the reader, whether their address was verified, when they opened it, how long they read, how far they scrolled, and their country and device where recorded. The sender's own previews and internal viewers are left out, as on the website. Pass `share_id` for one link; without it every link of the document is included. A very long answer is cut at a whole record and gives a `continue_from` value: call again with the same arguments and that value for the next rows, until it says it is every row. For a quick answer about who read one link, get_share_activity is shorter. It changes nothing.", + "description": "Returns the reading records the HTMLRadar website exports as a spreadsheet, as CSV text: for readers shown in full, one row per section per read (a read with no section recorded has one row with the section columns blank; section_status says \"not measured\" when the page changed while it was being read, so no section time was taken), with the link's label and slug, the reader, whether their address was verified, when they opened it, how long they read, how far they scrolled, and their country and device where recorded; proved_by says how each read got in (code, microsoft, google, password, address, personal, open or \"not recorded\") and signed_in_at when that sign-in happened (blank where there was none or it was not recorded); read_version, the last column, is the version of the page the read began on (a number, \"live page\" for a hosted page, blank where it was not recorded). On Free, the first five readers of a link are shown in full; later readers appear in a \"more read it\" count row without their individual details. The sender's own previews and internal viewers are left out, as on the website. With `share_id`, the records cover one link; without it every link of the document is included. A very long answer is cut at a whole record and gives a `continue_from` value for the remaining rows. The website file itself holds only the oldest 5,000 reads of a document or link, and the result says when it is every row of that file and when the file is capped. It changes nothing. It is the full export; get_share_activity summarises one link.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "The `continue_from` value a previous answer gave, to read the rows after it. Omit it to start from the first row.", + "description": "The `continue_from` value a previous answer gave selects the rows after it. Omission starts from the first row.", "type": "string" }, "document_id": { - "description": "The document — the document id from list_documents or list_shares.", + "description": "The document: the document id from list_documents or list_shares.", "type": "string" }, "share_id": {
--- pinned/get_share +++ observed/get_share { "annotations": { + "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "Read a tracked link's settings" - "description": "Returns a tracked link's current settings, in the form update_share changes them: who can open it (the full allowed-domain and allowed-address lists), the email gate and its one-time code, whether a password is set (never the password), the end date, the copy lock, comments, the label, who the gate names, whether the sender is emailed on the first open, and the settings version. It reads one of this account's links and changes nothing. The answer includes the saved Rules line and the version used by expected_settings_version.", + "description": "Returns a tracked link's current settings, in the form update_share changes them: who can open it (the full allowed-domain and allowed-address lists), the email gate and its one-time code, whether a password is set (never the password), the end date, the copy lock, comments, the label, who the gate names, whether the sender is emailed on the first open, and the settings version. It reads one of this account's links and changes nothing. The answer includes the saved rules and the settings version that update_share takes as expected_settings_version.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "The share id, the share's slug (the part after /r/ in its link), or the link itself. list_shares returns all three.", + "description": "The link's share id, slug (the part after /r/), or full address.", "type": "string" } },
--- pinned/get_share_activity +++ observed/get_share_activity { "annotations": { + "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "Check who read a tracked link" - "description": "Reports whether a tracked HTMLRadar link has been opened, by whom, for how long, how far they scrolled, and which sections held their attention. Per viewer it names the all recorded sections, ordered by reading time. Reading times are rounded down; scroll percentages are rounded to the nearest whole percent. It accepts a share id, a slug or a link; list_shares returns all three.", + "description": "Reports whether a tracked HTMLRadar link has been opened and how many read it. For each reader shown in full, it reports who they are, how long they read, how far they scrolled, and all recorded sections ordered by reading time. On Free, the first five readers of a link are shown in full; later readers appear as a \"more read it\" count. Reading times are rounded down; scroll percentages are rounded to the nearest whole percent. It accepts the link's share id, slug or full address. With `include_detail`, each reader shown in full has their country, city, device and referring page added.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "Also return each reader's country, city, device and referrer. Off by default: that is a named person's location and device, and whether the document was read and which parts of it is answered without them.", + "description": "Also return each reader's country, city, device and referrer. Off by default; whether the document was read, and which parts, is answered without it.", "type": "boolean" }, "share_id": {
--- pinned/list_attachments +++ observed/list_attachments { "annotations": { + "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "List a document's attached files" - "description": "Lists the files attached to a document on HTMLRadar (supporting materials a reader can download beside the page): the file name, its size and the attachment id that remove_attachment takes. It returns no file contents and changes nothing. Call it before add_attachment or remove_attachment, and after an add that failed without an answer.", + "description": "Lists the files attached to a document on HTMLRadar (supporting materials a reader can download beside the page): the file name, its size and the attachment id. It returns no file contents and changes nothing. After an add_attachment call that gave no answer, this list shows whether the file was attached.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "The document — the document id from list_documents or list_shares.", + "description": "The document: the document id from list_documents or list_shares.", "type": "string" } },
--- pinned/list_documents +++ observed/list_documents { "annotations": { + "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "List documents on this account" - "description": "Lists the account's documents, newest first: the title, when it was created, how many tracked links point at it, and the document id that create_share and replace_document take. A document with no links appears here and nowhere else, because list_shares only knows documents that have been sent. It returns no document contents. Returns at most 50 per call; the `before` cursor pages back through older documents.", + "description": "Lists the account's documents, newest first: the title, when it was created, how many tracked links point at it, and its document id. A document with no links appears here and not in list_shares, which lists only documents that have been sent. It returns no document contents. Returns at most 50 per call; the `before` cursor pages back through older documents.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "Cursor for the next page: the `next_before` value printed at the end of a previous list_documents result, of the form <created_at>|<document id>. Pass it back exactly as printed. Omit for the most recent documents.", + "description": "Cursor for the next page: the `next_before` value printed at the end of a previous list_documents result, of the form <created_at>|<document id>. Its exact value selects the next page; omission selects the most recent documents.", "type": "string" } },
--- pinned/list_shares +++ observed/list_shares { "annotations": { + "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, "title": "List tracked links on this account" - "description": "Lists the account's tracked links, newest first: the slug, the recipient label, the document title, whether it has been opened and when, and the share and document ids the other tools take. This is where the identifiers for a link made in an earlier conversation come from. The `opened` and `last_open` fields answer \"which of my links has nobody opened\" on their own, without a get_share_activity report for each one. Returns at most 50 per call; the `before` cursor pages back through older links.", + "description": "Lists the account's tracked links, newest first: the slug, the recipient label, the document title, whether it has been opened and when, and the share and document ids for each link. A link made in an earlier conversation is found here. The `opened` and `last_open` fields show which links nobody has opened. Returns at most 50 per call; the `before` cursor pages back through older links.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "Cursor for the next page: the `next_before` value printed at the end of a previous list_shares result, of the form <created_at>|<share id>. Pass it back exactly as printed. Omit for the most recent links.", + "description": "Cursor for the next page: the `next_before` value printed at the end of a previous list_shares result, of the form <created_at>|<share id>. Its exact value selects the next page; omission selects the most recent links.", "type": "string" } },
--- pinned/remove_attachment +++ observed/remove_attachment { "annotations": { "destructiveHint": true, - "description": "Removes one attached file from a document. Readers lose the download from the next time they load the page. It removes the file only: the page, its links and its reading history are untouched, and there is no tool that deletes a page or a link. Claude cannot restore it, and it cannot be recovered from HTMLRadar, so attach it again from the original if the user changes their mind. Take the attachment id from list_attachments.", + "description": "Removes one attached file from a document. Downloads stop at once, even from a page a reader already has open; the file leaves the page's list the next time the page loads. Copies a reader already downloaded stay with them. It removes the file only: the page, its links and its reading history are untouched, and there is no tool that deletes a page or a link. The file cannot be recovered from HTMLRadar; attaching it again needs the original file. list_attachments returns the attachment id.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "The document the file is attached to — from list_documents or list_shares.", + "description": "The document the file is attached to: from list_documents or list_shares.", "type": "string" } },
--- pinned/replace_document +++ observed/replace_document { "annotations": { "destructiveHint": true, - "description": "Replaces the contents of a document already on HTMLRadar. Every existing link stays exactly as it is — same address, same settings, same reading history — and serves the new contents from the next time it is opened, so nobody is sent a second link. The new HTML is screened for phishing signals as every upload is, and the previous version stays listed in the document's version history on the website. Restoring an earlier version is not available, from Claude or on the website; to go back, replace the contents again with the earlier page. Recipients may already have read the old contents. Pass either the whole new page in `html`, or `edits`: pieces of text to find in the page get_document returned, each with its replacement and each appearing exactly once. Edits suit small changes to a large page, because only the changes travel. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", + "description": "Replaces the contents of a document already on HTMLRadar, which is how a page that has been sent is updated. Every existing link stays exactly as it is (same address, same settings, same reading history) and serves the new contents from the next time it is opened, so nobody is sent a second link; a link that is switched off or past its end date stays closed. The new HTML is screened for phishing signals as every upload is, and readers of a page the screen holds see that it is not available yet. The previous version stays listed in the document's version history on the website. There is no restore, from Claude or on the website; going back means replacing the contents again with the earlier page. On a free account each document includes three new versions, so one replacement should carry every change the user asked for; a replacement answered with version_limit replaced nothing. Recipients may already have read the old contents. The call needs `expected_version`, the version get_document or list_documents shows, so a newer version is never overwritten. The tool accepts either the whole new page in `html`, up to 5 MB with its images as references, or `edits`: pieces of text to find in the page get_document returned, each with its replacement and each appearing exactly once. Past 5 MB, only `edits` work, because only the changes travel. A change to a page already on HTMLRadar is made by reading it with get_document and sending back the edited short form, or only the `edits`: that works for pages up to 30 MB, the same limit as the website, and keeps every image; a whole new file is needed only to replace the page itself. A page with more than 20 MB of text and code besides its images cannot be read or changed here, and a change that would take a page past that is refused, so nothing is stored. Images that need a login, expiring image addresses and local file paths do not load for readers of the link; an image embedded in the HTML as a data URI travels inside the page. The tool does not check that images load. On an update, embedded PNG, JPEG, GIF and WebP images appear as short htmlradar-image references in the document contents. Unchanged references restore the original images, so only new images count towards the 5 MB limit. Other embedded images, such as SVG, stay in the markup and count towards it.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "Tell readers what changed and alert subscribers. Omit to announce only when every live link is company-only; otherwise the replacement is quiet.", + "description": "Whether readers see what changed and subscribers receive an alert. Omitted means an announcement only when every live link is company-only; otherwise the replacement is quiet.", "type": "boolean" }, "document_id": { - "description": "Changes to the page get_document returned, applied in order. Each `find` must appear exactly once in the page at that point. Between 1 and 200. Pass this or `html`.", + "description": "Changes to the page get_document returned, applied in order. Each `find` must appear exactly once in the page at that point. Between 1 and 200. Mutually exclusive with `html`.", "items": { "properties": { "find": { - "description": "The new HTML markup, in full. It may keep the htmlradar-image references get_document returned. Pass this or `edits`, not both.", + "description": "The new HTML markup, in full. It may keep the htmlradar-image references get_document returned. Mutually exclusive with `edits`.", "type": "string" }, "note": { - "description": "Leave unset on a first attempt. When a previous call failed saying it may still have been applied, pass the request_id that error named: the retry then returns the first result instead of doing it twice.", + "description": "Optional on a first attempt. When a previous call may have been applied, the request_id named by its error makes a retry return the first result instead of doing it twice.", "type": "string" } },
--- pinned/revoke_share +++ observed/revoke_share { "annotations": { "destructiveHint": true, - "description": "Switches off a tracked link that has already been sent. Anyone who opens it afterwards sees that it is no longer available, and the sender is emailed that somebody tried. This changes what a recipient can see. It is reversible — `revoked: false` switches the link back on, so use this tool to turn a switched-off link on again — and it deletes nothing: the link, its settings and its whole reading history survive. Deleting a link is possible only on the website, because it deletes its reading records for good. To change a link's settings, use update_share on the same link: switching one off to make a replacement leaves the recipient holding a dead address.", + "description": "Switches off a tracked link that has already been sent. It is only for a user who asks to switch a link off, and never a stand-in for a request to delete a page or a link, which is possible only on the website. Anyone who opens it afterwards sees that it is no longer available, and the sender is emailed that somebody tried, at most once every six hours for a link. This changes what a recipient can see. It is reversible: `revoked: false` switches a link back on, however long ago it was switched off, but a link past its end date stays closed until update_share sets a new end date or clears it. It deletes nothing: the link, its settings and its whole reading history survive. Deleting a link is possible only on the website, because it deletes its reading records for good. update_share changes a link's settings without changing its address; switching one off to make a replacement leaves the recipient holding a dead address.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "The share id, the share's slug (the part after /r/ in its link), or the link itself. list_shares returns all three.", + "description": "The link's share id, slug (the part after /r/), or full address.", "type": "string" } },
--- pinned/share_html +++ observed/share_html { "annotations": { "destructiveHint": false, - "description": "Publishes an HTML document — a deck, report, dashboard, proposal or one-pager — as a tracked HTMLRadar link, and returns two addresses: the link for the recipient, and a dashboard address for the sender. The recipient sees the document as written and never the tracking. The markup goes in `html`; there is no file-path argument, so a document on disk reaches this tool only as markup the caller has already read, which leaves the user's permissions on their own file tools in charge of what is published. By default the recipient is asked for their email address before the document opens, which is a step the person receiving the link has to take. The link is live the moment it is returned. The answer includes the saved rules and comments state. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", + "description": "Publishes an HTML document (a deck, report, dashboard, proposal or one-pager) as a tracked HTMLRadar link, and returns two addresses: the link for the recipient, and a dashboard address for the sender. The recipient sees the document as written and never the tracking. The markup goes in `html`; there is no file-path argument, so a file on disk is published by passing its markup. By default the recipient is asked for their email address before the document opens. The new HTML is screened for phishing signals as every upload is; the link is live the moment it is returned unless the screen holds the page, and readers of a held page see that it is not available yet. The answer includes the saved rules and whether comments are on. The document id that create_share and replace_document take comes from list_documents or list_shares. Markup is limited to 5 MB. Images that need a login, expiring image addresses and local file paths do not load for readers of the link; an image embedded in the HTML as a data URI travels inside the page. The tool does not check that images load.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "Only these exact addresses may open the link, e.g. [\"ravi@acme.com\"]. A separate list from the domains, and a visitor passes on either. Up to 500 addresses; past that a domain is the right tool. Needs the email gate, which is on by default; with it off the call is refused.", + "description": "Only these exact addresses may open the link. A separate list from the domains, and a visitor passes on either. Up to 500 addresses; an allowed domain covers all addresses in that domain. Needs the email gate, which is on by default; with it off the call is refused.", "items": { "type": "string" }, - "description": "Blocks save and print and adds a watermark; default true. Pass false for a document the recipient is meant to keep a copy of.", + "description": "Blocks save and print; default true. False allows a recipient to keep a copy.", "type": "boolean" }, "password": { - "description": "Who this link is for, e.g. \"Acme\". One link per recipient reads best.", + "description": "Who this link is for. A separate link for each recipient separates their reading reports.", "type": "string" }, "request_id": { - "description": "Leave unset on a first attempt. When a previous call failed saying it may still have been applied, pass the request_id that error named: the retry then returns the first result instead of doing it twice.", + "description": "Optional on a first attempt. When a previous call may have been applied, the request_id named by its error makes a retry return the first result instead of doing it twice.", "type": "string" }, "require_email": { - "description": "Ask the recipient for their email before the document opens. Defaults to true.", + "description": "Whether the recipient must give an email address before the document opens. Defaults to true.", "type": "boolean" }, + "show_watermark": { + "description": "Show a faint watermark when lock_deck is true. Defaults to true on creation; omitted on edit keeps the saved choice.", + "type": "boolean" + }, "slug": { "description": "Custom link name, so the URL reads /r/acme-proposal. Paid plans only.", "type": "string" - "description": "Name shown on your dashboard. Recipients do not see it.", + "description": "The document's name on your dashboard. Readers can see it too: it names the page in the one-time code email they receive.", "type": "string" }, "verify_email": { - "description": "Verify that the address really is the reader's: we email a six-digit code and open the document only when the reader types it back. Off by default. Use it when the list of who opened the document has to be true rather than merely typed. Needs the email gate, which is on by default; with it off the call is refused.", + "description": "Whether the reader must prove their email address with a six-digit code before the document opens. Off by default. A verified address identifies the reader rather than an address merely typed into the gate. Needs the email gate, which is on by default; with it off the call is refused.", "type": "boolean" } },
--- pinned/update_share +++ observed/update_share { "annotations": { "destructiveHint": true, - "description": "Changes the settings of a tracked link that has already been sent, on the same link: who can open it (allowed domains and addresses), the email gate and its one-time code, the password, the end date, the copy lock, the label, who the gate names and whether the sender is emailed on the first open. Comments can be on or off; enabling needs a code-confirmed email gate. The answer includes the saved Rules line. The link, its address and its whole reading history stay the same. Only the settings you name change; every other setting is left as it is, and a setting is removed only when it is named in `clear`. The list arguments add_allowed_emails, remove_allowed_emails, add_allowed_email_domains and remove_allowed_email_domains: the server merges them over the stored list and says what was added, removed and not found. Sending allowed_emails or allowed_email_domains replaces the whole list and needs expected_settings_version from get_share, so a change made since is never overwritten. A stale version is refused without saving. A change applies from the next time the page is loaded: someone reading it right now keeps the page they have until they reload. If the sender is on a company team, the team's rules apply to this change exactly as on the website (for example a required one-time code or company domains), and a change that breaks one is refused with the rule named. Narrowing who can open a link, or removing a list, changes what recipients can see.", + "description": "Changes the settings of a tracked link that has already been sent, on the same link: who can open it (allowed domains and addresses), the email gate and its one-time code, the password, the end date, the copy lock, the label, who the gate names and whether the sender is emailed on the first open. Comments can be on or off; enabling needs a code-confirmed email gate. The answer includes the saved rules. The link, its address and its whole reading history stay the same. Only the settings named in the call change; every other setting is left as it is, and a setting is removed when it is named in `clear` (a recipient_label of only spaces also removes the label). The list arguments add_allowed_emails, remove_allowed_emails, add_allowed_email_domains and remove_allowed_email_domains: the server merges them over the stored list and says what was added, removed and not found. Replacing or clearing a whole list (sending allowed_emails or allowed_email_domains, or naming one in `clear`) needs expected_settings_version, the settings version get_share returned, so a change made since is never overwritten. A stale version is refused without saving. A change applies from the next time the page is loaded: someone reading it right now keeps the page they have until they reload. If the sender is on a company team, the team's rules apply to this change exactly as on the website (for example a required one-time code or company domains), and a change that breaks one is refused with the rule named. Narrowing who can open a link, or removing a list, changes what recipients can see.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "description": "Only these email domains may open the link, e.g. [\"acme.com\"]. This REPLACES the whole stored list: call get_share first and send the domains that should stay with the new one. To remove the list, use `clear`. Needs the email gate on.", + "description": "Only these email domains may open the link, e.g. [\"acme.com\"]. This REPLACES the whole stored list, so entries absent from this value are removed. `clear` removes the list. Needs the email gate on.", "items": { "type": "string" }, - "description": "Only these exact addresses may open the link. A separate list from the domains; a visitor passes on either. This REPLACES the whole stored list: call get_share first and send the addresses that should stay with the new one. To remove the list, use `clear`. Needs the email gate on.", + "description": "Only these exact addresses may open the link. A separate list from the domains; a visitor passes on either. This REPLACES the whole stored list, so entries absent from this value are removed. `clear` removes the list. Needs the email gate on.", "items": { "type": "string" }, - "description": "Settings to remove: the label, the password, the end date, the domain list, the address list. Removing a list lets anyone who passes the email gate in, so say so to the user first. A setting that is not named here or above is left exactly as it is.", + "description": "Settings to remove: the label, the password, the end date, the domain list, the address list. Removing a list lets anyone who passes the email gate in. A setting that is not named here or above is left exactly as it is.", "items": { "enum": [ "recipient_label", - "description": "The settings version get_share showed. The change is made only if the link is still at that version; otherwise nothing is changed and you are told to call get_share again. Required when you replace or clear a whole list (allowed_emails, allowed_email_domains).", + "description": "The settings version get_share showed. The change is made only if the link is still at that version; if the settings changed since they were read, nothing is changed and the call returns the current settings version. Required when a whole allowed-address or allowed-domain list is replaced or cleared.", "maximum": 9007199254740991, "minimum": 0, "type": "integer" - "description": "When the link stops working, as a date and time such as 2026-12-31T17:00:00Z. Give this or `expires_in_hours`. To remove the end date, use `clear`.", + "description": "When the link stops working, as a date and time such as 2026-12-31T17:00:00Z. Mutually exclusive with `expires_in_hours`. `clear` removes the end date.", "type": "string" }, "expires_in_hours": { - "description": "The link stops working this many hours from now. Give this or `expires_at`.", + "description": "The link stops working this many hours from now. Mutually exclusive with `expires_at`.", "exclusiveMinimum": 0, "type": "number" }, - "description": "The copy lock: true blocks save and print and adds a watermark; false allows them.", + "description": "The copy lock: true blocks save and print; false allows them.", "type": "boolean" }, "notify_first_open": { - "description": "Whether the sender is emailed when someone first opens this link.", + "description": "Whether the sender is e-mailed when someone reads this link.", "type": "boolean" }, "password": { - "description": "Set a password (at least 8 characters) on top of the email gate. To remove one, use `clear`.", + "description": "A password of at least 8 characters on top of the email gate. `clear` removes it.", "minLength": 8, "type": "string" }, - "description": "Addresses to REMOVE from the stored list of allowed addresses. The answer says which were not on the list. Removing the last entry of every list is refused; use `clear` for that.", + "description": "Addresses to REMOVE from the stored list of allowed addresses. The answer says which were not on the list. Removing the last entry of every list is refused; `clear` removes a whole list.", "items": { "type": "string" }, - "description": "Turn the email gate on or off. Turning it off removes the check that the list of allowed domains and addresses relies on, so clear those in the same call.", + "description": "Whether the email gate is on. Turning it off removes the check that the list of allowed domains and addresses relies on; those lists must be cleared in the same call.", "type": "boolean" }, "share_id": { - "description": "The share id, the share's slug (the part after /r/ in its link), or the link itself. list_shares returns all three.", + "description": "The link's share id, slug (the part after /r/), or full address.", "type": "string" }, "show_sender": { + "show_watermark": { + "description": "Show a faint watermark when lock_deck is true. Defaults to true on creation; omitted on edit keeps the saved choice.", + "type": "boolean" + }, "verify_email": { - "description": "Turn the one-time-code check on or off: we email the reader a six-digit code and open the document only when they type it back. Needs the email gate on.", + "description": "Whether the one-time-code check is on: the reader receives a six-digit code and opens the document only when they type it back. Needs the email gate on.", "type": "boolean" } },
--- pinned/whoami +++ observed/whoami { "annotations": { + "destructiveHint": false, "openWorldHint": true, "readOnlyHint": true, - "title": "Show the HTMLRadar plan and free links left" + "title": "Show the HTMLRadar plan and free links used" }, - "description": "Reports which HTMLRadar account the API key belongs to (its email address), the plan it is on and how many of its free tracked links remain.", + "description": "Reports which HTMLRadar account the API key belongs to (its email address), the plan it is on and how many of its free tracked links it has used out of the free allowance, or that tracked links are unlimited. It also reports what this connection may do (read only, or read and publish), any notice about the plan, and any notice about a newer version of the HTMLRadar package.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {}, - "title": "Show the HTMLRadar plan and free links left" + "title": "Show the HTMLRadar plan and free links used" }
Changed 2026-10-23 11:51 UTC
7 descriptions rewritten.
--- pinned/create_share +++ observed/create_share { "annotations": { "destructiveHint": false, - "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Creates an additional tracked link for a document already on HTMLRadar, with its own recipient label, gate, password, expiry and address. One link per recipient is what separates their reading reports. It uploads nothing and creates no second copy of the document, and it cannot publish new markup: it takes a document id, which list_shares returns and share_html returned when the document was first published. The link is live the moment it is returned.", + "description": "Creates an additional tracked link for a document already on HTMLRadar, with its own recipient label, gate, password, expiry and address. One link per recipient is what separates their reading reports. It uploads nothing and creates no second copy of the document, and it cannot publish new markup: it takes a document id, which list_shares returns and share_html returned when the document was first published. The link is live the moment it is returned. The answer includes the saved rules and comments state.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { + "comments": { + "description": "Whether readers can comment. Off by default. Turning comments on needs the email gate and a one-time code; who sees comments follows the link.", + "enum": [ + "on", + "off" + ], + "type": "string" + }, "document_id": { "description": "The document to make another link for — the document id from list_shares, or the one share_html returned when the document was first published.", "type": "string"
--- pinned/get_share +++ observed/get_share { "annotations": { "openWorldHint": true, - "description": "Returns a tracked link's current settings, in the form update_share changes them: who can open it (the full allowed-domain and allowed-address lists), the email gate and its one-time code, whether a password is set (never the password), the end date, the copy lock, the label, who the gate names, whether the sender is emailed on the first open, and the settings version. It reads one of this account's links and changes nothing. Pass the settings version to update_share as expected_settings_version when it replaces a whole list.", + "description": "Returns a tracked link's current settings, in the form update_share changes them: who can open it (the full allowed-domain and allowed-address lists), the email gate and its one-time code, whether a password is set (never the password), the end date, the copy lock, comments, the label, who the gate names, whether the sender is emailed on the first open, and the settings version. It reads one of this account's links and changes nothing. The answer includes the saved Rules line and the version used by expected_settings_version.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {
--- pinned/list_shares +++ observed/list_shares { "annotations": { "openWorldHint": true, - "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Lists the account's tracked links, newest first: the slug, the recipient label, the document title, whether it has been opened and when, and the share and document ids the other tools take. This is where the identifiers for a link made in an earlier conversation come from. The `opened` and `last_open` fields answer \"which of my links has nobody opened\" on their own, without a get_share_activity report for each one. Returns at most 50 per call; the `before` cursor pages back through older links.", + "description": "Lists the account's tracked links, newest first: the slug, the recipient label, the document title, whether it has been opened and when, and the share and document ids the other tools take. This is where the identifiers for a link made in an earlier conversation come from. The `opened` and `last_open` fields answer \"which of my links has nobody opened\" on their own, without a get_share_activity report for each one. Returns at most 50 per call; the `before` cursor pages back through older links.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {
--- pinned/replace_document +++ observed/replace_document { "annotations": { "destructiveHint": true, - "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Replaces the contents of a document already on HTMLRadar. Every existing link stays exactly as it is — same address, same settings, same reading history — and serves the new contents from the next time it is opened, so nobody is sent a second link. The new HTML is screened for phishing signals as every upload is, and the previous version stays listed in the document's version history on the website. Restoring an earlier version is not available, from Claude or on the website; to go back, replace the contents again with the earlier page. Recipients may already have read the old contents. Pass either the whole new page in `html`, or `edits`: pieces of text to find in the page get_document returned, each with its replacement and each appearing exactly once. Edits suit small changes to a large page, because only the changes travel. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", + "description": "Replaces the contents of a document already on HTMLRadar. Every existing link stays exactly as it is — same address, same settings, same reading history — and serves the new contents from the next time it is opened, so nobody is sent a second link. The new HTML is screened for phishing signals as every upload is, and the previous version stays listed in the document's version history on the website. Restoring an earlier version is not available, from Claude or on the website; to go back, replace the contents again with the earlier page. Recipients may already have read the old contents. Pass either the whole new page in `html`, or `edits`: pieces of text to find in the page get_document returned, each with its replacement and each appearing exactly once. Edits suit small changes to a large page, because only the changes travel. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {
--- pinned/share_html +++ observed/share_html { "annotations": { "destructiveHint": false, - "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Publishes an HTML document — a deck, report, dashboard, proposal or one-pager — as a tracked HTMLRadar link, and returns two addresses: the link for the recipient, and a dashboard address for the sender. The recipient sees the document as written and never the tracking. The markup goes in `html`; there is no file-path argument, so a document on disk reaches this tool only as markup the caller has already read, which leaves the user's permissions on their own file tools in charge of what is published. By default the recipient is asked for their email address before the document opens, which is a step the person receiving the link has to take. The link is live the moment it is returned. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", + "description": "Publishes an HTML document — a deck, report, dashboard, proposal or one-pager — as a tracked HTMLRadar link, and returns two addresses: the link for the recipient, and a dashboard address for the sender. The recipient sees the document as written and never the tracking. The markup goes in `html`; there is no file-path argument, so a document on disk reaches this tool only as markup the caller has already read, which leaves the user's permissions on their own file tools in charge of what is published. By default the recipient is asked for their email address before the document opens, which is a step the person receiving the link has to take. The link is live the moment it is returned. The answer includes the saved rules and comments state. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { + "comments": { + "description": "Whether readers can comment. Off by default. Turning comments on needs the email gate and a one-time code; who sees comments follows the link.", + "enum": [ + "on", + "off" + ], + "type": "string" + }, "expires_in_hours": { "description": "Link stops working after this many hours.", "exclusiveMinimum": 0,
--- pinned/update_share +++ observed/update_share { "annotations": { "destructiveHint": true, - "description": "Changes the settings of a tracked link that has already been sent, on the same link: who can open it (allowed domains and addresses), the email gate and its one-time code, the password, the end date, the copy lock, the label, who the gate names and whether the sender is emailed on the first open. Use this instead of making a new link and switching the old one off. The link, its address and its whole reading history stay the same. Only the settings you name change; every other setting is left as it is, and a setting is removed only when it is named in `clear`. To add or remove addresses or domains, use add_allowed_emails, remove_allowed_emails, add_allowed_email_domains and remove_allowed_email_domains: the server merges them over the stored list and says what was added, removed and not found. Sending allowed_emails or allowed_email_domains replaces the whole list and needs expected_settings_version from get_share, so a change made since is never overwritten. If the answer says the link was changed, call get_share again and re-apply the change from what it shows. A change applies from the next time the page is loaded: someone reading it right now keeps the page they have until they reload. If the sender is on a company team, the team's rules apply to this change exactly as on the website (for example a required one-time code or company domains), and a change that breaks one is refused with the rule named. Narrowing who can open a link, or removing a list, changes what recipients can see.", + "description": "Changes the settings of a tracked link that has already been sent, on the same link: who can open it (allowed domains and addresses), the email gate and its one-time code, the password, the end date, the copy lock, the label, who the gate names and whether the sender is emailed on the first open. Comments can be on or off; enabling needs a code-confirmed email gate. The answer includes the saved Rules line. The link, its address and its whole reading history stay the same. Only the settings you name change; every other setting is left as it is, and a setting is removed only when it is named in `clear`. The list arguments add_allowed_emails, remove_allowed_emails, add_allowed_email_domains and remove_allowed_email_domains: the server merges them over the stored list and says what was added, removed and not found. Sending allowed_emails or allowed_email_domains replaces the whole list and needs expected_settings_version from get_share, so a change made since is never overwritten. A stale version is refused without saving. A change applies from the next time the page is loaded: someone reading it right now keeps the page they have until they reload. If the sender is on a company team, the team's rules apply to this change exactly as on the website (for example a required one-time code or company domains), and a change that breaks one is refused with the rule named. Narrowing who can open a link, or removing a list, changes what recipients can see.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { + "comments": { + "description": "Whether readers can comment. Omitted keeps the current choice. Turning comments on needs the email gate and a one-time code; who sees comments follows the link.", + "enum": [ + "on", + "off" + ], + "type": "string" + }, "expected_settings_version": { "description": "The settings version get_share showed. The change is made only if the link is still at that version; otherwise nothing is changed and you are told to call get_share again. Required when you replace or clear a whole list (allowed_emails, allowed_email_domains).", "maximum": 9007199254740991,
--- pinned/whoami +++ observed/whoami { "annotations": { "openWorldHint": true, - "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Reports which HTMLRadar account the API key belongs to (its email address), the plan it is on and how many of its free tracked links remain.", + "description": "Reports which HTMLRadar account the API key belongs to (its email address), the plan it is on and how many of its free tracked links remain.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {},
Changed 2026-10-20 11:43 UTC
5 descriptions rewritten.
--- pinned/create_share +++ observed/create_share { "annotations": { "destructiveHint": false, - "description": "Creates an additional tracked link for a document already on HTMLRadar, with its own recipient label, gate, password, expiry and address. One link per recipient is what separates their reading reports. It uploads nothing and creates no second copy of the document, and it cannot publish new markup: it takes a document id, which list_shares returns and share_html returned when the document was first published. The link is live the moment it is returned.", + "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Creates an additional tracked link for a document already on HTMLRadar, with its own recipient label, gate, password, expiry and address. One link per recipient is what separates their reading reports. It uploads nothing and creates no second copy of the document, and it cannot publish new markup: it takes a document id, which list_shares returns and share_html returned when the document was first published. The link is live the moment it is returned.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {
--- pinned/list_shares +++ observed/list_shares { "annotations": { "openWorldHint": true, - "description": "Lists the account's tracked links, newest first: the slug, the recipient label, the document title, whether it has been opened and when, and the share and document ids the other tools take. This is where the identifiers for a link made in an earlier conversation come from. The `opened` and `last_open` fields answer \"which of my links has nobody opened\" on their own, without a get_share_activity report for each one. Returns at most 50 per call; the `before` cursor pages back through older links.", + "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Lists the account's tracked links, newest first: the slug, the recipient label, the document title, whether it has been opened and when, and the share and document ids the other tools take. This is where the identifiers for a link made in an earlier conversation come from. The `opened` and `last_open` fields answer \"which of my links has nobody opened\" on their own, without a get_share_activity report for each one. Returns at most 50 per call; the `before` cursor pages back through older links.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {
--- pinned/replace_document +++ observed/replace_document { "annotations": { "destructiveHint": true, - "description": "Replaces the contents of a document already on HTMLRadar. Every existing link stays exactly as it is — same address, same settings, same reading history — and serves the new contents from the next time it is opened, so nobody is sent a second link. The new HTML is screened for phishing signals as every upload is, and the previous version stays listed in the document's version history on the website. Restoring an earlier version is not available, from Claude or on the website; to go back, replace the contents again with the earlier page. Recipients may already have read the old contents. Pass either the whole new page in `html`, or `edits`: pieces of text to find in the page get_document returned, each with its replacement and each appearing exactly once. Edits suit small changes to a large page, because only the changes travel. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", + "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Replaces the contents of a document already on HTMLRadar. Every existing link stays exactly as it is — same address, same settings, same reading history — and serves the new contents from the next time it is opened, so nobody is sent a second link. The new HTML is screened for phishing signals as every upload is, and the previous version stays listed in the document's version history on the website. Restoring an earlier version is not available, from Claude or on the website; to go back, replace the contents again with the earlier page. Recipients may already have read the old contents. Pass either the whole new page in `html`, or `edits`: pieces of text to find in the page get_document returned, each with its replacement and each appearing exactly once. Edits suit small changes to a large page, because only the changes travel. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {
--- pinned/share_html +++ observed/share_html { "annotations": { "destructiveHint": false, - "description": "Publishes an HTML document — a deck, report, dashboard, proposal or one-pager — as a tracked HTMLRadar link, and returns two addresses: the link for the recipient, and a dashboard address for the sender. The recipient sees the document as written and never the tracking. The markup goes in `html`; there is no file-path argument, so a document on disk reaches this tool only as markup the caller has already read, which leaves the user's permissions on their own file tools in charge of what is published. By default the recipient is asked for their email address before the document opens, which is a step the person receiving the link has to take. The link is live the moment it is returned. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", + "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Publishes an HTML document — a deck, report, dashboard, proposal or one-pager — as a tracked HTMLRadar link, and returns two addresses: the link for the recipient, and a dashboard address for the sender. The recipient sees the document as written and never the tracking. The markup goes in `html`; there is no file-path argument, so a document on disk reaches this tool only as markup the caller has already read, which leaves the user's permissions on their own file tools in charge of what is published. By default the recipient is asked for their email address before the document opens, which is a step the person receiving the link has to take. The link is live the moment it is returned. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {
--- pinned/whoami +++ observed/whoami { "annotations": { "openWorldHint": true, - "description": "Reports which HTMLRadar account the API key belongs to (its email address), the plan it is on and how many of its free tracked links remain.", + "description": "If a result has a line starting 'For the user:', tell the user once, in your own words, and say nothing more about it. Reports which HTMLRadar account the API key belongs to (its email address), the plan it is on and how many of its free tracked links remain.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {},
Changed 2026-10-19 13:09 UTC
4 descriptions rewritten, 7 tools added.
+ tool added: add_attachment
--- pinned/get_document +++ observed/get_document { "annotations": { "openWorldHint": true, - "description": "Returns the current contents of a document on HTMLRadar so they can be changed and put back with replace_document. Each image embedded as a data URI appears as a short htmlradar-image reference instead of its data; keep references exactly as they are. It reads only this account's documents and changes nothing.", + "description": "Returns the current contents of a document on HTMLRadar so they can be changed and put back with replace_document. Each image embedded as a data URI appears as a short htmlradar-image reference instead of its data; keep references exactly as they are. A page over 5 MB of text even with its images as references is too large to read whole; with `query`, a word or phrase from the part to change, any page returns only the passages where that text appears, which replace_document `edits` can then change. It reads only this account's documents and changes nothing.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { + }, + "query": { + "description": "Text to find, 1 to 200 characters, matched literally with letter case ignored, such as a product name or a price. Returns up to 20 passages around the matches, and how many there are, instead of the whole page: the way to edit a page too large to read whole.", + "maxLength": 200, + "minLength": 1, + "type": "string" } }, "required": [
+ tool added: get_page_guidelines
+ tool added: get_reading_records
+ tool added: get_share
--- pinned/get_share_activity +++ observed/get_share_activity { "annotations": { "openWorldHint": true, - "description": "Reports whether a tracked HTMLRadar link has been opened, by whom, for how long, how far they scrolled, and which sections held their attention. Per viewer it names the five sections with the most reading time, and every figure is rounded down, so no number it prints is above the recorded one. It accepts a share id, a slug or a link; list_shares returns all three.", + "description": "Reports whether a tracked HTMLRadar link has been opened, by whom, for how long, how far they scrolled, and which sections held their attention. Per viewer it names the all recorded sections, ordered by reading time. Reading times are rounded down; scroll percentages are rounded to the nearest whole percent. It accepts a share id, a slug or a link; list_shares returns all three.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": {
+ tool added: list_attachments
+ tool added: remove_attachment
--- pinned/replace_document +++ observed/replace_document { "annotations": { "destructiveHint": true, - "description": "Replaces the contents of a document already on HTMLRadar. Every existing link stays exactly as it is — same address, same settings, same reading history — and serves the new contents from the next time it is opened, so nobody is sent a second link. The new HTML is screened for phishing signals as every upload is, and the previous version is kept in the document's history. Recipients may already have read the old contents. Pass either the whole new page in `html`, or `edits`: pieces of text to find in the page get_document returned, each with its replacement and each appearing exactly once. Edits suit small changes to a large page, because only the changes travel. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", + "description": "Replaces the contents of a document already on HTMLRadar. Every existing link stays exactly as it is — same address, same settings, same reading history — and serves the new contents from the next time it is opened, so nobody is sent a second link. The new HTML is screened for phishing signals as every upload is, and the previous version stays listed in the document's version history on the website. Restoring an earlier version is not available, from Claude or on the website; to go back, replace the contents again with the earlier page. Recipients may already have read the old contents. Pass either the whole new page in `html`, or `edits`: pieces of text to find in the page get_document returned, each with its replacement and each appearing exactly once. Edits suit small changes to a large page, because only the changes travel. Images that need a login, expiring image addresses and local file paths do not load for readers of the link. Images embedded in the HTML as data URIs always do. On an update, get_document shows each embedded image as a short htmlradar-image reference; keep each one exactly as it is and HTMLRadar puts the image back, so only new images count towards the 5 MB limit.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { + "announce": { + "description": "Tell readers what changed and alert subscribers. Omit to announce only when every live link is company-only; otherwise the replacement is quiet.", + "type": "boolean" + }, "document_id": { "description": "The document whose contents are being replaced. Every link to it keeps working.", "type": "string" - "description": "Text in the page get_document returned, copied exactly.", + "description": "Text in the page or passages get_document returned, copied exactly; it must appear exactly once in the whole page.", "type": "string" }, "replace": { + "note": { + "description": "Optional note for an announced update, at most 140 characters.", + "type": "string" + }, "request_id": { "description": "Leave unset on a first attempt. When a previous call failed saying it may still have been applied, pass the request_id that error named: the retry then returns the first result instead of doing it twice.", "type": "string"
--- pinned/revoke_share +++ observed/revoke_share { "annotations": { "destructiveHint": true, - "title": "Switch a tracked link off" + "title": "Switch a tracked link off, or back on" }, - "description": "Switches off a tracked link that has already been sent. Anyone who opens it afterwards sees that it is no longer available, and the sender is emailed that somebody tried. This changes what a recipient can see. It is reversible — `revoked: false` switches the link back on — and it deletes nothing: the link, its settings and its whole reading history survive. Deleting a link is possible only on the website. A link’s settings cannot be changed after it is made, and switching one off to create a replacement carrying different settings leaves the recipient holding a dead address, so that is a swap the user agrees to explicitly rather than a way to edit a setting.", + "description": "Switches off a tracked link that has already been sent. Anyone who opens it afterwards sees that it is no longer available, and the sender is emailed that somebody tried. This changes what a recipient can see. It is reversible — `revoked: false` switches the link back on, so use this tool to turn a switched-off link on again — and it deletes nothing: the link, its settings and its whole reading history survive. Deleting a link is possible only on the website, because it deletes its reading records for good. To change a link's settings, use update_share on the same link: switching one off to make a replacement leaves the recipient holding a dead address.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "properties": { - "title": "Switch a tracked link off" + "title": "Switch a tracked link off, or back on" }
+ tool added: update_share
Current tools
Show all 16 tool fingerprints
add_attachment
create_share
get_document
get_page_guidelines
get_reading_records
get_share
get_share_activity
list_attachments
list_documents
list_shares
remove_attachment
replace_document
revoke_share
share_html
update_share
whoami
Watch this server yourself
If you run this server, put the proxy in front of it. It pins these exact fingerprints on first connect and stops the session if they move.
npx -y mcp-pin@0.2.4 -- <your htmlradar-mcp command>
Or subscribe to this page's RSS feed to be told when it changes.
Badge
The badge states one fact about time and nothing else. It never claims a server is safe.
[](https://mcp-pin.gautamkhosla.com/servers/0c7dc1893c0e82f5.html)