Medical Terminologies MCP

Deep Research Search

search

Read-onlyIdempotent

Searches the medical terminologies (CID-10 categories and chapters, ICD-11, LOINC, RxNorm, MeSH, terminology version records) catalog and returns up to 10 matching documents as { id, title, url }, ordered by relevance (an empty list means nothing matched).

This tool exists for the OpenAI Deep Research contract: ChatGPT deep research, company knowledge and research workflows over the Responses API require exactly the tools search and fetch. Pass one of the returned ids to fetch to read the document. For direct questions and for data (values, series, rankings) prefer the terminology tools (icd11_*, cid10_*, loinc_*, rxnorm_*, mesh_*, atc_*, map_*, find_equivalent, validate_codes), which return the actual data with provenance — this is a catalog index, not a data query.

Query: natural language or keywords, Portuguese or English; accents and case are ignored.

Behavior: read-only and idempotent — the catalog comes from the public source and is cached in memory.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	Search terms, natural language or keywords (accents and case are ignored)

Output Schema

TableJSON Schema

Name	Required	Description
`results`	Yes	Matching documents, in relevance order
`provenance`	Yes	One provenance block per upstream source that contributed to this response (contract v1.1; licenses are never merged; each block carries the origin diagnostics of ITS source)
`attribution`	Yes	Canonical source URLs of this response (attribution list)

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 27, 2026

changedOutput schema / properties / provenance / description

Previous value: -"One provenance block per upstream source that contributed to this response (contract v1.0; licenses are never merged)"New value: +"One provenance block per upstream source that contributed to this response (contract v1.1; licenses are never merged; each block carries the origin diagnostics of ITS source)"

addedOutput schema / properties / provenance / items / description

Added value: +"Bloco de proveniência (contrato v1.1): fonte, URL, competência, extração, diagnóstico de origem, citação e licença"

addedOutput schema / properties / provenance / items / properties / retrieval

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "anomalies": {
+          "description": "Anomalias superadas até o sucesso, somadas por classe, em ordem fixa; [] se nenhuma",
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "count": {
+                "description": "Ocorrências desta classe na chamada",
+                "maximum": 9007199254740991,
+                "minimum": 1,
+                "type": "integer"
+              },
+              "kind": {
+                "description": "Classe da anomalia (vocabulário fechado do contrato)",
+                "enum": [
+                  "timeout",
+                  "network",
+                  "http_4xx",
+                  "http_5xx",
+                  "rate_limited",
+                  "malformed_body"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "kind",
+              "count"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "attempts": {
+          "description": "Tentativas somadas, incluindo as repetidas (>= requests)",
+          "maximum": 9007199254740991,
+          "minimum": 1,
+          "type": "integer"
+        },
+        "requests": {
+          "description": "Idas distintas à origem que compõem esta resposta (fatias, páginas)",
+          "maximum": 9007199254740991,
+          "minimum": 1,
+          "type": "integer"
+        },
+        "unstable": {
+          "description": "true se houve repetição (attempts > requests) ou alguma anomalia",
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "requests",
+        "attempts",
+        "anomalies",
+        "unstable"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Origin diagnostics of THIS source in this call (contract v1.1): requests made to the upstream, attempts summed across retries, anomalies worked around (kind + count); unstable=true when any anomaly happened. null when nothing was measured (bundled dataset, or response served entirely from cache)"
+}

changedOutput schema / properties / provenance / items / required

Previous value: -[
-  "source",
-  "source_url",
-  "data_vintage",
-  "retrieved_at",
-  "citation",
-  "license"
-]New value: +[
+  "source",
+  "source_url",
+  "data_vintage",
+  "retrieved_at",
+  "retrieval",
+  "citation",
+  "license"
+]

First observedSep 6, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/openWorld/idempotent/destructive=false, so safety is covered. The description adds genuine behavioral context beyond them: a cap of 10 results, relevance ordering, empty-list semantics, and in-memory caching of a public-source catalog. Return field format is also stated, though that partly overlaps the output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then usage contract, then scope warning, then parameter and behavior notes. The Deep Research contract paragraph is a little dense but earns its place by justifying existence alongside richer siblings. No wasted sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be re-explained, and the description nonetheless covers result count, ordering, empty behavior, and the fetch follow-up. Purpose, usage, and behavior are all complete for a single-param search entry point.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single param is fully documented there. The description's note that queries accept natural language, Portuguese or English, with accents/case ignored largely repeats the schema's own parameter text, so it adds little beyond the structured field. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (searches) and resource (the medical terminologies catalog), names the exact data domains covered (CID-10, ICD-11, LOINC, RxNorm, MeSH, version records), and describes the return shape. It also explicitly distinguishes itself from the terminology tools, so an agent can tell what this is versus the ~30 siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use (the OpenAI Deep Research contract requiring exactly `search` and `fetch`), when-not-to-use (direct questions and actual data should use the terminology tools), and names those alternatives. The `fetch` handoff for returned ids is spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Medical Terminologies MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.