Public log

@ask-llm/mcp

Unified MCP server for multi-LLM consultation — routes Gemini, Codex, Claude, Grok, Ollama, and Antigravity behind runtime availability checks

npm · fingerprint aff1cc9d0453e6cdbdc1e983 · repository · RSS

6tools
2recorded versions
45dtracked
last checked 13 Oct

What changed

Changed between 4 September 2026 and 5 October 2026 (first seen 2026-10-05 14:37 UTC)

2 schema or annotation changes with the description left byte-identical.

--- pinned/ask-llm
+++ observed/ask-llm
  {
    "annotations": {
      "destructiveHint": false,
+       "preferred": {
+         "description": "Codex-only: opt into ASK_CODEX_PREFERRED_MODEL when it differs from the default. Unsupported on other providers; never silently stripped. Leave unset for normal review calls.",
+         "type": "boolean"
+       },
        "prompt": {
          "description": "The question, code review request, or analysis task to send",
          "maxLength": 100000,
-         "description": "Which LLM provider to use. Available: \"gemini\" (Gemini, default model: gemini-3.1-pro-preview), \"codex\" (Codex, default model: gpt-5.6-sol), \"claude\" (Claude, default model: opus), \"grok\" (Grok, default model: grok-4.6), \"ollama\" (Ollama, default model: qwen3.6:27b), \"antigravity\" (Antigravity, default model: gemini-3.1-pro)",
+         "description": "Which LLM provider to use. Available: \"gemini\" (Gemini, default model: gemini-3.1-pro-preview), \"codex\" (Codex, default model: gpt-6-astra), \"claude\" (Claude, default model: opus), \"grok\" (Grok, default model: grok-4.7), \"ollama\" (Ollama, default model: qwen3.8:27b), \"antigravity\" (Antigravity, default model: gemini-3.1-pro)",
          "enum": [
            "gemini",
            "codex",
-         "description": "Provider-native reasoning effort. Codex accepts low/medium/high/xhigh/max; Grok accepts low/medium/high/xhigh. Unsupported provider/effort combinations are rejected, never stripped.",
+         "description": "Provider-native reasoning effort. Codex accepts low/medium/high/xhigh/max/ultra; Grok accepts low/medium/high/xhigh. Unsupported provider/effort combinations are rejected, never stripped.",
          "enum": [
            "low",
            "medium",
-           "max"
+           "max",
+           "ultra"
          ],
          "type": "string"
        },
+       "sandbox": {
+         "description": "Codex-only sandbox. Defaults to the executor's read-only review contract when omitted. Set workspace-write only for explicit write flows such as image generation. Unsupported on other providers; never silently stripped.",
+         "enum": [
+           "read-only",
+           "workspace-write"
+         ],
+         "type": "string"
+       },
        "sessionId": {
          "description": "Optional session ID. For Codex, pass \"\" on the first call to create a persisted thread, then pass its returned Thread ID to resume; omitting it makes the call ephemeral. For other session-capable providers, pass a prior Session ID to resume. Claude/Gemini use --resume, Codex uses exec resume, and Ollama uses server-side replay. Grok and Antigravity are one-shot.",
          "type": "string"
--- pinned/diagnose
+++ observed/diagnose
  {
    "annotations": {
      "destructiveHint": false,
+             "enrichment": {
+               "additionalProperties": false,
+               "properties": {
+                 "checks": {
+                   "items": {
+                     "additionalProperties": false,
+                     "properties": {
+                       "name": {
+                         "type": "string"
+                       },
+                       "remediation": {
+                         "type": "string"
+                       },
+                       "status": {
+                         "enum": [
+                           "pass",
+                           "warn",
+                           "fail",
+                           "skip"
+                         ],
+                         "type": "string"
+                       },
+                       "summary": {
+                         "type": "string"
+                       }
+                     },
+                     "required": [
+                       "name",
+                       "status",
+                       "summary"
+                     ],
+                     "type": "object"
+                   },
+                   "type": "array"
+                 },
+                 "heading": {
+                   "type": "string"
+                 },
+                 "overall": {
+                   "enum": [
+                     "ok",
+                     "warning",
+                     "error"
+                   ],
+                   "type": "string"
+                 }
+               },
+               "required": [
+                 "heading",
+                 "overall",
+                 "checks"
+               ],
+               "type": "object"
+             },
              "error": {
                "type": "string"
              },

Current tools

Show all 6 tool fingerprints
ask-cursor-agent
8dd3f5e185db4d80
ask-llm
9153d3542e005db5
diagnose
a6823a7de9c8e15f
get-usage-stats
a0cca3c620d23c5a
multi-llm
0c1d38730be7bb47
ping
f19d447972f13a10

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@0.2.3 -- <your @ask-llm/mcp command>

Or subscribe to this page's RSS feed to be told when it changes.

Badge

mcp-pin status badge for @ask-llm/mcp

The badge states one fact about time and nothing else. It never claims a server is safe.

[![mcp-pin](https://mcp-pin.gautamkhosla.com/badge/c363ec5ed3191e2f.svg)](https://mcp-pin.gautamkhosla.com/servers/c363ec5ed3191e2f.html)