PubMed MCP Server

Tools

Seven tools for working with PubMed and NCBI data:

pubmed_search

Search PubMed with full NCBI query syntax and filters.

• Free-text queries with PubMed's full boolean and field-tag syntax

• Field-specific filters: author, journal, MeSH terms, language, species

• Common filters: has abstract, free full text

• Date range filtering by publication, modification, or Entrez date

• Publication type filtering (Review, Clinical Trial, Meta-Analysis, etc.)

• Sort by relevance, publication date, author, or journal

• Pagination via offset for paging through large result sets

• Optional brief summaries for top N results via ESummary

pubmed_fetch

Fetch full article metadata by PubMed IDs.

• Batch fetch up to 200 articles at once (auto-switches to POST for large batches)

• Returns structured data: title, abstract, authors with deduplicated affiliations, journal info, DOI

• Direct links to PubMed and PubMed Central (when available)

• Optional MeSH terms, grant information, and publication types

• Handles PubMed's inconsistent XML (structured abstracts, missing fields, varying date formats)

pubmed_pmc_fetch

Fetch full-text articles from PubMed Central (PMC).

• Accepts PMC IDs directly or PubMed IDs (auto-resolved to PMCIDs via ELink)

• Returns complete article body text organized by sections and subsections

• Optional reference list from back matter

• Section filtering by title (case-insensitive match, e.g. ["methods", "results"])

• Configurable max sections to limit response size

• Up to 10 articles per request

• Only open-access articles available in PMC will return full text

pubmed_cite

Generate formatted citations for articles.

• Four citation styles: APA 7th, MLA 9th, BibTeX, RIS

• Request multiple styles per article in a single call

• Hand-rolled formatters — zero external dependencies, fully Workers-compatible

• Up to 50 articles per request

pubmed_related

Find articles related to a source article via ELink.

• Three relationship types: similar (content similarity), cited_by, references

• Results enriched with title, authors, publication date, and source via ESummary

• Similarity scores included for similar relationship type

pubmed_spell

Spell-check a biomedical query using NCBI's ESpell.

• Returns the original query, corrected query, and whether a suggestion was found

• Useful for query refinement before searching

pubmed_mesh_lookup

Search and explore the MeSH (Medical Subject Headings) vocabulary.

• Search MeSH terms by name with exact-heading matching

• Detailed records with tree numbers, scope notes, and entry terms by default

• Useful for building precise PubMed queries with controlled vocabulary

Related MCP server: MedAdapt Content Server

Resource and prompt

Features

Built on mcp-ts-template 3.0:

• Declarative tool definitions — single file per tool, framework handles registration and validation

• Unified McpError error handling across all tools

• Pluggable auth (none, jwt, oauth)

• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1

• Structured logging (Pino) with optional OpenTelemetry tracing

• Typed DI container with Token<T> phantom branding

• Runs locally (stdio/HTTP) or on Cloudflare Workers from the same codebase

PubMed-specific:

• Complete NCBI E-utilities integration (ESearch, EFetch, ESummary, ELink, ESpell, EInfo)

• Sequential request queue with configurable delay for NCBI rate limit compliance

• NCBI-specific XML parser with isArray hints for PubMed's inconsistent XML structure

• Hand-rolled citation formatters (APA, MLA, BibTeX, RIS) — zero deps, Workers-compatible

Getting started

Public Hosted Instance

A public instance is available at https://pubmed.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "pubmed": {
      "type": "streamable-http",
      "url": "https://pubmed.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "pubmed": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/pubmed-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "NCBI_API_KEY": "your-key-here"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "pubmed": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/pubmed-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "NCBI_API_KEY": "your-key-here"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "pubmed": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/pubmed-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3017 bun run start:http
# Server listens at http://localhost:3017/mcp

Prerequisites

• Bun v1.3.2 or higher.

• Optional: NCBI API key for higher rate limits (10 req/s vs 3 req/s).

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/pubmed-mcp-server.git

2. Navigate into the directory:

cd pubmed-mcp-server

3. Install dependencies:

bun install

Configuration

All configuration is centralized and validated at startup in src/config/index.ts. Key environment variables:

Running the server

Local development

• Build and run the production version:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:http
  # or
  bun run start:stdio

• Run checks and tests:

  bun run devcheck  # Lints, formats, type-checks, and more
  bun run test      # Runs the test suite

Cloudflare Workers

1. Build the Worker bundle:

bun run build:worker

2. Run locally with Wrangler:

bun run deploy:dev

3. Deploy to Cloudflare:

   bun run deploy:prod

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Logic throws McpError, handlers catch — no try/catch in tool logic

• Pass RequestContext through the call stack for logging and tracing

• Register new tools and resources in the index.ts barrel files

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.