The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Medical Terminologies MCP listing page.
A Model Context Protocol (MCP) server providing unified access to major global medical terminologies:
Ask your assistant:
icd11_searchmap_icd10_to_icd11loinc_detailscid10_searchThe answers come from authoritative sources (WHO, NLM, NIH, DataSUS) — real codes and mappings, not guesses from training data.
search/fetch for ChatGPT Deep Researchfind-medical-code, drug-info, cid10-portuguese-lookup) — clients render these as one-click user actionsinfo://server, info://cid10/chapters, info://licenses, info://stats) — sub-millisecond reads (except info://stats which round-trips to the StatsCounter Durable Object on the hosted endpoint)structuredContent.provenance + attribution, mirrored in _meta under com.sidneybissoli.medical/*, with a compact text footer for text-only clients. Multi-source responses (find_equivalent, validate_codes) carry one block per source; server-computed ranking fields are flagged as derivedhttps://medical.sidneybissoli.com/mcp, or your own instance of worker/)📖 Article (in Portuguese): CID-10, CID-11 e o que muda para quem trabalha com dados do SUS — the V2008 structure in numbers, what the WHO transition tables are and are not, and the licences that differ between sources. Also published on the site, in Portuguese and English: sidneybissoli.com.
This server is not a clinical-care decision tool — practicing clinicians have specialized assistants (UpToDate AI, OpenEvidence, EHR-integrated tools) for that. The actual audience is researchers, public-health analysts, clinical informatics developers, and educators who need programmatic access to authoritative terminology data.
| If you're a... | Start with | Why |
|---|---|---|
| Biomedical researcher / bibliographer | mesh_search, mesh_descriptor, mesh_tree | MeSH is PubMed's indexing vocabulary; tree numbers let you traverse the controlled hierarchy programmatically |
| Public-health analyst (Brazil / SUS) | cid10_search, cid10_chapters, atc_classify | CID-10 V2008 is the Brazilian operational standard; ATC pairs cleanly with DataSUS prescription data |
| Public-health analyst (international) | icd11_search, icd11_lookup, icd11_chapters | WHO ICD-11 is the current international revision; chapters and hierarchy support pipeline classification |
| Clinical-informatics developer | loinc_search, loinc_details, find_equivalent | LOINC for lab/observation interoperability; cross-terminology search to scaffold new mappings |
| Educator / curriculum author | mesh_descriptor, icd11_lookup, rxnorm_search | Authoritative definitions, tree numbers, and drug term-types you can drop into self-checked exercises |
A public Cloudflare Workers deployment runs at:
Connect via the MCP Inspector or any Streamable HTTP MCP client:
Or install via Smithery, which proxies the same endpoint through their gateway:
The hosted instance has WHO credentials configured, so all 33 default tools work without any setup on your side. For your own deployment (e.g. corporate network, different region, custom WHO credentials), see the Installation and Hosted on Cloudflare Workers sections below.
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
| Variable | Required | Description |
|---|---|---|
WHO_CLIENT_ID | Yes¹ | WHO ICD API Client ID |
WHO_CLIENT_SECRET | Yes¹ | WHO ICD API Client Secret |
WHO_ICD11_RELEASE_ID | No | ICD-11 release to query (e.g. 2025-01, 2026-01). Default 2026-01. |
ENABLE_SNOMED_TOOLS | No² | Set to true to register the 6 SNOMED-dependent tools. Default off. |
SNOMED_BASE_URL | No² | Base URL for a Snowstorm instance, e.g. https://my-snowstorm.example.com/snowstorm/snomed-ct. |
SNOMED_LANGUAGE | No² | Accept-Language tag(s) for SNOMED responses, e.g. pt, pt-BR, es. Default en. Single-tag values are pass-through reliably; composite values with q-weights (e.g. pt-BR,en;q=0.8) depend on your Snowstorm instance's Accept-Language handling — fallback semantics may vary. Test against your specific deployment if relying on weighted fallback. |
LOG_LEVEL | No | pino log level (debug, info, warn, error, fatal). Default info. |
¹ Required for ICD-11 tools. Get credentials at: https://icd.who.int/icdapi.
² See SNOMED CT setup (advanced) below. LOINC, RxNorm, and MeSH need no configuration.
The server runs over stdio by default — that's what Claude Desktop and IDE clients expect. The Streamable HTTP transport is served by the Cloudflare Worker in worker/ (an instance of the maintainer's Fase 0 hosting template). The --http flag of the Node entry was removed in v1.6.0 — if you need a local HTTP endpoint, run the Worker locally:
Hosted endpoints (production and local alike):
POST /mcp — JSON-RPC over Streamable HTTP (the MCP protocol). Stateless mode: each request is independent.GET /health — liveness probe returning { status, name, version, tool_count, uptime_s }.GET /status — version + deploy metadata. GET /metrics — aggregated per-tool usage.GET /stats and GET /stats/badge — public tool-call counter (since 2026-05-13) and its shields.io badge.GET /.well-known/mcp/server-card.json — static server card for registry scanners.*) so browser clients (e.g. the MCP Inspector web UI) can connect directly.ChatGPT deep research (and company knowledge, and research workflows over the Responses API) only uses an MCP server that exposes exactly search and fetch — this server does, on top of the terminology tools. Point the connector at the hosted endpoint, no key required:
search ranks the query across the bundled CID-10 (categories, subcategories, chapters), the terminology version records and a live fan-out to ICD-11, LOINC, RxNorm and MeSH (the same fan-out find_equivalent does; a source that fails is skipped) and returns { id, title, url }; fetch renders the document through the terminology's own lookup tool (cid10_lookup, icd11_lookup, loinc_details, rxnorm_concept, mesh_descriptor, terminology_versions) as readable Markdown with the canonical public page (WHO ICD browsers, loinc.org, RxNav, MeSH Browser), which is what ChatGPT cites. Both carry the same provenance block as every other tool — search one block per source that answered, like find_equivalent. SNOMED is not part of the corpus (its public browser retired, so there is no page to cite). In ChatGPT's developer mode (Settings → Security and login → Developer mode) any tool is callable — the terminology tools remain the ones to use for data.
The production deployment is the Cloudflare Worker in worker/, config in worker/wrangler.jsonc, CI deploy in .github/workflows/deploy-worker.yml (auto-runs on every push to main).
To deploy your own instance:
Note: worker/wrangler.jsonc pins the maintainer's account_id and custom domain route — remove/replace both for your own deployment.
Why Workers: zero cold start at the edge, $5/mo flat for 10M requests (free tier covers up to 100k req/day), and no VMs to size or restart. The template ships per-IP rate limiting and a usage-stats Durable Object; the upstream-facing cache/rate-limiter are per-isolate (PROGRESS.md Phase 11.9 Stage 2 tracks the KV/DO upgrade).
After your Worker is live, register the URL on Smithery:
https://smithery.ai/new).https://<your-worker>.workers.dev/mcp. Smithery's gateway scans for compliance and proxies traffic.The server never machine-translates terminology content — but several sources publish official translations, and the tools expose them:
cid10_search / cid10_lookup / cid10_chapter(s) serve the DataSUS V2008 dataset (the CID-10 the Brazilian SUS uses operationally).language: "pt" to icd11_search / icd11_lookup to search and read WHO's official pt-BR linearization labels.language: "pt" to mesh_search / mesh_descriptor to request NLM's official translations where they exist.language requests the descriptions loaded in your Snowstorm edition (e.g. a national extension's pt-BR refset).If a source has no official translation for an entry, you get the source language back — never a machine translation.
| Tool | Description | Example |
|---|---|---|
icd11_search | Search ICD-11 by term | query: "diabetes mellitus" |
icd11_lookup | Get entity details by code/URI | code: "5A11" |
icd11_hierarchy | Navigate parent/child relationships | code: "5A11" |
icd11_chapters | List all ICD-11 chapters | - |
icd11_postcoordination | Get postcoordination axes | code: "5A11" |
| Tool | Description | Example |
|---|---|---|
loinc_search | Search lab tests and observations | query: "glucose" |
loinc_details | Get full LOINC code details | loinc_num: "2339-0" |
loinc_answers | Get answer list for surveys | loinc_num: "44249-1" |
loinc_panels | Get panel/form structure | loinc_num: "24331-1" |
| Tool | Description | Example |
|---|---|---|
rxnorm_search | Search drugs by name | query: "metformin" |
rxnorm_concept | Get drug concept details | rxcui: "6809" |
rxnorm_ingredients | Get active ingredients | rxcui: "6809" |
rxnorm_classes | Get therapeutic classes | rxcui: "6809" |
rxnorm_ndc | Map between RxCUI and NDC | rxcui: "6809" |
| Tool | Description | Example |
|---|---|---|
mesh_search | Search MeSH descriptors | query: "hypertension" |
mesh_descriptor | Get descriptor details | mesh_id: "D006973" |
mesh_tree | Get tree hierarchy location | mesh_id: "D006973" |
mesh_qualifiers | Get allowed qualifiers | mesh_id: "D006973" |
These are only registered when ENABLE_SNOMED_TOOLS=true. See SNOMED CT setup (advanced).
| Tool | Description | Example |
|---|---|---|
snomed_search | Search concepts by term | query: "myocardial infarction" |
snomed_concept | Get concept details by SCTID | sctid: "22298006" |
snomed_hierarchy | Get parent/child concepts | sctid: "22298006" |
snomed_descriptions | Get all descriptions | sctid: "22298006" |
snomed_ecl | Execute ECL queries | ecl: "<< 73211009" |
map_snomed_to_icd10 requires SNOMED)| Tool | Description | Example |
|---|---|---|
map_icd10_to_icd11 | Authoritative ICD-10 → ICD-11 mapping via bundled WHO transition tables; returns primary code + chapter + URIs and any WHO-documented alternatives | icd10_code: "E11" |
map_snomed_to_icd10 | SNOMED CT → ICD-10 guidance (only when ENABLE_SNOMED_TOOLS=true) | sctid: "73211009" |
map_loinc_to_snomed | LOINC ↔ SNOMED guidance | loinc_code: "2339-0" |
validate_codes | Batch-validate up to 100 codes across ICD-11, LOINC, RxNorm, MeSH, ATC, CID-10 (and SNOMED when enabled); returns per-code valid/invalid + display name | codes: [{terminology:"icd11",code:"5A11"}, …] |
find_equivalent | Ranked unified search across terminologies: server-computed match_score/rank per candidate plus cross-terminology groups of lexically identical titles; SNOMED branch is skipped when SNOMED tools are disabled | term: "diabetes" |
WHO Anatomical Therapeutic Chemical classification, served through NLM RxClass (free, no auth). The WHOCC base itself requires a paid subscription, but RxClass envelopes the same code/name pairs.
| Tool | Description | Example |
|---|---|---|
atc_classify | Drug name → ATC code(s) | drug_name: "metformin" |
atc_lookup | ATC code (level 1-4) → name + level type | atc_code: "A10BA" |
atc_members | ATC class → member drugs | atc_code: "A10BA" |
Brazilian Portuguese translation of ICD-10 (DataSUS V2008). Bundled as a static dataset — no HTTP calls. The Brazilian SUS uses CID-10 V2008 operationally; for the international ICD-11 (current WHO revision), use the ICD-11 tools above.
| Tool | Description | Example |
|---|---|---|
cid10_search | Portuguese text search (diacritic-insensitive) | query: "diabetes" |
cid10_lookup | Code → official Portuguese name | code: "I21" or "A00.1" |
cid10_chapters | List the 22 CID-10 chapters | - |
cid10_chapter | Chapter detail with constituent groups | num: 9 |
Surface what version of each terminology this server queries against today — useful when running batch validation against a pinned release or when investigating an unexpected lookup miss after an upstream update.
| Tool | Description | Example |
|---|---|---|
terminology_versions | List all 8 supported terminologies with current version, release date, publisher, source URL, and update cadence | - |
terminology_diff | Report what diff data is available between two versions of a terminology (real cross-revision stats for ICD-10 → ICD-11; guidance otherwise) | terminology: "icd10-icd11" |
The OpenAI Deep Research contract — the only two tools without a terminology prefix (names fixed by OpenAI). See ChatGPT (Deep Research) above.
| Tool | Description | Example |
|---|---|---|
search | Searches the catalog (CID-10, ICD-11, LOINC, RxNorm, MeSH, terminology versions) and returns { id, title, url } ranked by relevance | query: "myocardial infarction" |
fetch | Returns the full document of an id from search ({ id, title, text, url, metadata }), rendered by the terminology's lookup tool | id: "cid10:I21.0" |
The samples below are the actual formatted output the tools produce — the text body of the CallToolResult. Tools also return a structuredContent object matching each tool's outputSchema for programmatic consumers.
loinc_search — query: "glucose", max_results: 3total_count (1024) reflects every match in the NLM Clinical Tables index, not just the page returned. Bump max_results (max 50) to see canonical codes like 2339-0 (Glucose [Mass/volume] in Blood); the API's relevance ranking puts panels and derived measurements above plain blood-glucose at small page sizes.
rxnorm_ingredients — rxcui: "6809" (metformin)For an RxCUI that is itself an ingredient (TTY=IN), the tool returns that ingredient plus every multi-ingredient (TTY=MIN) concept that includes it. Use this to enumerate combination products built around a substance.
mesh_descriptor — mesh_id: "D006973" (Hypertension)The scope note comes from the descriptor's preferred concept, not its annotation field (which is an indexer-facing note). Tree numbers are the navigable path into MeSH's controlled hierarchy — C14.907.489 places Hypertension under Cardiovascular Diseases → Vascular Diseases.
icd11_search with a clinical term → pick the result → icd11_lookup with the code for full details, or icd11_hierarchy to walk parents/children.rxnorm_search for a brand or generic name → rxnorm_concept for the canonical record → rxnorm_ingredients and rxnorm_classes for downstream analysis.find_equivalent with a clinical term searches ICD-11, LOINC, RxNorm, MeSH, and (when enabled) SNOMED in one call. Use it to bootstrap mappings; the pairwise map_* tools refine them.map_icd10_to_icd11 does honest text search against WHO ICD-11. Real WHO transition tables are tracked in PROGRESS.md Phase 13.1.The 5 SNOMED tools (snomed_search, snomed_concept, snomed_hierarchy, snomed_descriptions, snomed_ecl) plus the SNOMED-dependent crosswalk tool (map_snomed_to_icd10) are disabled by default. With them disabled, the server registers 33 tools instead of 39; find_equivalent still works and skips the SNOMED branch with an explanatory note.
The reason: as of 2026-05-08, the public IHTSDO Snowstorm endpoint that this project historically called (https://browser.ihtsdotools.org/snowstorm/snomed-ct/...) returns HTTP 410 Gone for every path. Without a working backend, registering these tools surfaces 6 guaranteed-broken tools to every client.
To enable the SNOMED tools:
Confirm your SNOMED CT license. SNOMED CT use requires an SNOMED International (IHTSDO) license. Member country residents typically have one through their national release center; non-members can obtain an Affiliate license. See https://www.snomed.org/snomed-ct/get-snomed.
Run a Snowstorm instance. SNOMED International publishes Snowstorm as open source (IHTSDO/snowstorm) and as a Docker image (snomedinternational/snowstorm). Self-hosting requires importing an RF2 release file (provided to license holders).
Configure this server:
SNOMED_BASE_URL should point at the base under which Snowstorm exposes its /MAIN/concepts and related endpoints. SNOMED_LANGUAGE accepts standard Accept-Language tags (e.g. pt, es, pt-BR,en;q=0.8) — Snowstorm returns localized terms when the branch has them and falls back to English otherwise.
Restart the MCP client so the server picks up the env vars.
If you set ENABLE_SNOMED_TOOLS=true without configuring a working Snowstorm, the SNOMED tools will register but every call will fail at the network layer.
The MIT license covers the server code and server-maintained metadata
only — not the terminology content served through it, and not
the two bundled datasets (cid10.json, icd10-to-icd11.json), which
remain under their own terms. The consolidated notice ships with the
package as NOTICE.md; every tool response carries a
per-source provenance block with the applicable license.
ICD-11 content is provided under the Creative Commons Attribution-NoDerivatives 3.0 IGO license (CC BY-ND 3.0 IGO), per the ICD-11 Terms of Use and License Agreement.
Format conversion (TSV → JSON, content unaltered) of the tables WHO publishes within the ICD-11 release. © World Health Organization, under the ICD-11 Terms of Use — not under this project's MIT license. WHO's guidance: the tables show correspondence between revisions and "are not intended for directly converting data from one revision to the other."
© World Health Organization; Brazilian Portuguese translation © CBCD / Faculdade de Saúde Pública da USP; electronic files published by DataSUS (Ministério da Saúde do Brasil). DataSUS/CBCD permission: developers may use the files with due credit and at no charge — this server serves them free with credit in every response. Not under this project's MIT license.
SNOMED CT use requires an IHTSDO (SNOMED International) license. The SNOMED tools in this server are disabled by default and only enabled by operators with a valid license and a self-hosted Snowstorm instance — see SNOMED CT setup (advanced).
This material contains content from LOINC (http://loinc.org). LOINC is copyright © Regenstrief Institute, Inc. and the Logical Observation Identifiers Names and Codes (LOINC) Committee and is available at no cost under the license at http://loinc.org/license. LOINC® is a registered United States trademark of Regenstrief Institute, Inc.
RxNorm is produced by the U.S. National Library of Medicine; the RxNav APIs serve non-proprietary, public-domain RxNorm content free of charge.
This product uses publicly available data from the U.S. National Library of Medicine (NLM), National Institutes of Health, Department of Health and Human Services; NLM is not responsible for the product and does not endorse or recommend this or any other product.
ATC classification © WHO Collaborating Centre for Drug Statistics Methodology (https://atcddd.fhi.no/), retrieved via NLM RxClass and served verbatim. This server never redistributes the WHOCC ATC/DDD index.
MeSH is a U.S. government work served under the NLM Terms and Conditions. Courtesy of the U.S. National Library of Medicine.
This server implements rate limiting to respect API providers:
| API | Rate Limit |
|---|---|
| WHO ICD-11 | 5 requests/second |
| NLM (LOINC, MeSH) | 10 requests/second |
| RxNorm | 20 requests/second |
| SNOMED CT (Snowstorm) | 10 requests/second |
Contributions are welcome! Please feel free to submit a Pull Request.
git checkout -b feature/AmazingFeature)git commit -m 'Add some AmazingFeature')git push origin feature/AmazingFeature)Sidney Bissoli
This project is licensed under the MIT License - see the LICENSE file for details.
Note: While this software is MIT licensed, the medical terminologies accessed through it have their own licenses (see Terminology Licenses above).
If you encounter any issues or have questions:
Made with love for the medical informatics community