A pasteable skeleton generated from the repository name. Check the project README for the exact package and arguments.
Star count
1 โ ยท qinisolabs/icdwise ยท read from the GitHub search API ยท (checked 2026-10-16 20:00:20)
Source
collected from the punkpeye/awesome-mcp-servers list ยท type: MCP server
Harvest history
first seen 2026-10-09 ยท last seen 2026-10-16 ยท seen 32ร ยท listed by 7 sources
Score
score 703 ยท 1 โ ยท 7 sources ยท mcp
FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP ๆๅก. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository qinisolabs/icdwise๏ผfirst catalogued 2026-10-09๏ผlast seen 2026-10-16ใThere is no official certification or quality rating here โ we record sources and dates only.
**Verified ICD-10-CM code lookup & validation for AI agents โ official descriptions, not guesses.** *Verified, trustworthy data tools for AI agents. "Qiniso" means "truth" in Zulu.* Website ยท npm ยท MCP endpoint ยท MCP Registry --- Ask an LLM what an ICD-10-CM code means and it will answer confidently โ and often **wrongly**: the wrong laterality, the wrong severity, the wrong condition entirely, and it will happily invent a description for a code that doesn't exist. **icdwise** looks the code up in the official U.S. ICD-10-CM code set and returns the real description โ or an honest *"not found"* instead of a guess. > Asked to describe real ICD-10-CM codes, a frontier model with no tools was **wrong ~38% of the time** โ e.g. it called H40.1131 *"severe stage, right eye"* (it's *mild, bilateral*) and T63.011A *"ingested mushrooms"* (it's *rattlesnake venom*) โ and it **fabricated a description for a code that doesn't exist**. icdwise: the official text, or "not found." Never a guess. Add it to Claude Settings โ Connectors โ **Add custom connector**, and paste โ no login, no key: Stateless, reads no user data, requires no secrets. Prefer to run it locally over stdio? Add { "command": "npx", "args": ["-y", "icdwise"] } under mcpServers in your client config. Use it as a library Codes are accepted with or without the dot (E11.9 or E119). A well-formed code that isn't in the official set returns found: false with a clear note โ it never invents a description. Tools โ 3 | Tool | What it answers | | --- | --- | | **lookup_icd10** | The official description of a code (+ canonical form and 3-char category) | | **validate_icd10** | Is this a real ICD-10-CM code? (well-formed *and* in the official set) | | **search_icd10** | Reverse lookup โ find the code(s) for a condition by keywords | Data ICD-10-CM is U.S. **public-domain** data (NCHS/CMS). The full code set (~74,000 codes) is bundled and generated from the official CMS release via npm run build-data (see scripts/build-data.mjs); every response reports the datasetVersion it used. Descriptions are the official text โ the curated, versioned dataset kept current is the moat. What it is *not* - **Not medical advice**, and not a determination of billability, coverage, or clinical appropriateness. - **Not ICD-10 (WHO) or ICD-11** โ this is ICD-10-**CM** (the U.S. Clinical Modification). - **Not a guesser** โ unknown/retired/non-leaf codes return an honest "not found", never a fabricated description.