Medical Terminologies MCP

Search MeSH

mesh_search

Read-onlyIdempotent

Find official MeSH medical subject headings to index literature, refine PubMed searches, and retrieve controlled vocabulary terms with IDs and labels.

Instructions

Search for MeSH (Medical Subject Headings) descriptors.

Use this tool to:

Find MeSH terms for indexing medical literature
Look up subject headings for PubMed searches
Find controlled vocabulary terms

Set language to request NLM's official translations where they exist (e.g. language: "pt" for Portuguese labels); content is never machine-translated.

Returns matching descriptors with MeSH IDs and labels.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`match`	No	Match type: exact, contains, or startswith. Default: contains	contains
`query`	Yes	Search term (e.g., "diabetes", "heart failure")
`language`	No	Language code (default: en). Returns the source's OFFICIAL translation when it exists (e.g. 'pt' for official Portuguese); content is never machine-translated.	en
`max_results`	No	Maximum number of results (1-100). Default: 25

Output Schema

TableJSON Schema

Name	Required	Description
`match`	Yes
`query`	Yes
`provenance`	Yes	Provenance block (contract v1.0): source, URL, data vintage, extraction instant, citation, license
`attribution`	Yes	Canonical source URLs of this response (attribution list)
`descriptors`	Yes
`total_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.9.1Sep 1, 2026
- removedOutput schema / properties / provenance / properties / data_vintage / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / provenance / properties / data_vintage / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / provenance / properties / license / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / provenance / properties / license / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed4 schema fields changedv1.8.0Aug 10, 2026

changedInput schema / properties / language / description

Previous value: -"Language code (default: en)"New value: +"Language code (default: en). Returns the source's OFFICIAL translation when it exists (e.g. 'pt' for official Portuguese); content is never machine-translated."

addedOutput schema / properties / attribution

Added value: +{
+  "description": "Canonical source URLs of this response (attribution list)",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / provenance

Added value: +{
+  "additionalProperties": false,
+  "description": "Provenance block (contract v1.0): source, URL, data vintage, extraction instant, citation, license",
+  "properties": {
+    "citation": {
+      "description": "Ready-to-use citation/attribution string",
+      "type": "string"
+    },
+    "data_vintage": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Version/release of the data as exposed by the source; null when not exposed"
+    },
+    "license": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "License / legal regime of the data"
+    },
+    "retrieved_at": {
+      "description": "Real instant of the upstream extraction (ISO-8601, UTC). Responses served from cache keep the ORIGINAL fetch instant.",
+      "type": "string"
+    },
+    "source": {
+      "description": "Official upstream source of this data",
+      "type": "string"
+    },
+    "source_url": {
+      "description": "Canonical URL of the source (API base or dataset release)",
+      "type": "string"
+    }
+  },
+  "required": [
+    "source",
+    "source_url",
+    "data_vintage",
+    "retrieved_at",
+    "citation",
+    "license"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "query",
-  "match",
-  "total_count",
-  "descriptors"
-]New value: +[
+  "query",
+  "match",
+  "total_count",
+  "descriptors",
+  "provenance",
+  "attribution"
+]

Changed3 schema fields changedv1.5.7Jun 21, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- addedOutput schema / properties / total_count / maximum
```
Added value: +9007199254740991
```
- addedOutput schema / properties / total_count / minimum
```
Added value: +-9007199254740991
```

Changed1 schema field changedv1.4.0May 12, 2026

addedInput schema / properties / language

Added value: +{
+  "default": "en",
+  "description": "Language code (default: en)",
+  "enum": [
+    "en",
+    "es",
+    "pt",
+    "fr",
+    "de",
+    "it",
+    "zh",
+    "ja",
+    "ar",
+    "ru"
+  ],
+  "type": "string"
+}

First observedv1.2.1May 11, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, non-destructive), so the bar is lower. The description adds genuine value beyond annotations: the guarantee that 'content is never machine-translated' and the return format ('matching descriptors with MeSH IDs and labels'). It does not cover pagination or error behavior, but for a search tool with strong annotation coverage, this is solid.

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?

The description is well-structured: core purpose first, then use cases, then the critical language caveat, then return format. It is compact with no wasted sentences. The bullet list slightly rephrases the opening line, but each bullet adds a distinct usage angle, so it earns its place.

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?

Given the presence of an output schema, annotations covering safety, and 100% schema param coverage, the description is complete. It states what is searched, why an agent would use it, the one non-obvious behavior (no machine translation), and what results contain. Nothing an agent needs to invoke it correctly is missing.

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 description coverage is 100%, so the baseline is 3. The description reinforces the language parameter's special behavior (official translations only, e.g., Portuguese), but that nuance is already documented in the schema's language property. The description adds no new parameter semantics beyond what the schema provides, so a 3 is appropriate.

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?

The opening sentence states a specific verb and resource: 'Search for MeSH (Medical Subject Headings) descriptors.' The bulleted use cases (indexing literature, PubMed searches, controlled vocabulary) further anchor what the tool does and differentiate it from domain-specific siblings like cid10_search or atc_lookup without needing to open their schemas.

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

Usage Guidelines4/5

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

The description gives clear context for when to use the tool via three concrete use cases, but it never names alternatives or states when NOT to use it (e.g., no routing to mesh_descriptor for looking up a specific known MeSH ID). This meets 'clear context, no exclusions,' which fits a 4.

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