PluginBench
MCP Server
Active
Apache-2.0

io.github.cyanheads/pubmed-mcp-server MCP Server

io.github.cyanheads/pubmed-mcp-server

Search PubMed, Europe PMC, and fetch full-text articles with citations and MeSH terms via MCP.

RepositoryRegistry
How to choose

What this kind of tool is for

  • Let your agent search the web or a document set and cite what it found.
  • Pull structured facts out of pages instead of copy-pasting by hand.
  • Track changes on a topic over days without re-reading everything.

How to compare servers like this

Source coverage:
Check which engines, sites, or document types the tool can actually reach.
Citation behavior:
Prefer tools that return links you can open, not just summarized claims.
Terms of service:
Some sources forbid automated access; make sure the tool stays inside them.
Maintenance signal:
Scrapers break silently when pages change; recent commits are the best proxy.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.cyanheads/pubmed-mcp-server MCP server?

The pubmed-mcp-server is an MCP server that provides access to PubMed, PubMed Central, and Europe PMC for searching biomedical literature, fetching article metadata and full text, and retrieving citations and MeSH vocabulary. It integrates NCBI E-utilities and supports multiple output formats for citations and structured full-text extraction.

This server enables AI agents to search and retrieve biomedical research articles from PubMed and Europe PMC, fetch full-text content from multiple sources (PMC, EPMC, Unpaywall), and work with citations and MeSH terms. It's useful for literature review, research synthesis, citation resolution, and building biomedical knowledge bases.

How to install io.github.cyanheads/pubmed-mcp-server

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • MCP_LOG_LEVEL

    Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').

  • NCBI_API_KEY

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

  • NCBI_ADMIN_EMAIL

    Contact email sent with NCBI requests (recommended by NCBI).

  • UNPAYWALL_EMAIL

    Contact email for Unpaywall. When set, pubmed_fetch_fulltext falls back to Unpaywall open-access copies for DOIs not in PMC.

  • MCP_HTTP_HOST

    The hostname for the HTTP server.

  • MCP_HTTP_PORT

    The port to run the HTTP server on.

  • MCP_HTTP_ENDPOINT_PATH

    The endpoint path for the MCP server.

  • MCP_PUBLIC_URL

    Public origin override for deployments behind a TLS-terminating reverse proxy (e.g. https://mcp.example.com).

  • MCP_AUTH_MODE

    Authentication mode to use: 'none', 'jwt', or 'oauth'.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "pubmed-mcp-server": {
      "command": "bun",
      "args": [
        "-y",
        "@cyanheads/pubmed-mcp-server",
        "run",
        "start:stdio"
      ],
      "env": {
        "MCP_LOG_LEVEL": "<YOUR_MCP_LOG_LEVEL>",
        "NCBI_API_KEY": "<YOUR_NCBI_API_KEY>",
        "NCBI_ADMIN_EMAIL": "<YOUR_NCBI_ADMIN_EMAIL>",
        "UNPAYWALL_EMAIL": "<YOUR_UNPAYWALL_EMAIL>",
        "MCP_HTTP_HOST": "<YOUR_MCP_HTTP_HOST>",
        "MCP_HTTP_PORT": "<YOUR_MCP_HTTP_PORT>",
        "MCP_HTTP_ENDPOINT_PATH": "<YOUR_MCP_HTTP_ENDPOINT_PATH>",
        "MCP_PUBLIC_URL": "<YOUR_MCP_PUBLIC_URL>",
        "MCP_AUTH_MODE": "<YOUR_MCP_AUTH_MODE>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • pubmed_search_articles — Search PubMed with full query syntax, field-specific filters, date ranges, pagination, and optional brief summaries
  • pubmed_europepmc_search — Search Europe PMC for preprints, patents, Agricola, and EPMC-only OA records with cursor-based pagination
  • pubmed_europepmc_fetch — Fetch complete Europe PMC records by source and epmcId with full untruncated abstracts
  • pubmed_fetch_articles — Fetch full article metadata by PMIDs including abstract, authors, journal, MeSH terms, and grants
  • pubmed_fetch_fulltext — Fetch full-text articles via NCBI PMC, Europe PMC, or Unpaywall with section filtering and character budgets
  • pubmed_format_citations — Generate formatted citations in APA 7th, MLA 9th, BibTeX, RIS, or Vancouver styles
  • pubmed_find_related — Find similar articles, citing articles, or references for a given PMID
  • pubmed_spell_check — Spell-check biomedical queries using NCBI's ESpell service
  • pubmed_lookup_mesh — Search and explore MeSH vocabulary with tree numbers, scope notes, and entry terms
  • pubmed_lookup_citation — Resolve partial bibliographic references to PubMed IDs via ECitMatch
  • pubmed_convert_ids — Convert between DOI, PMID, and PMCID using the PMC ID Converter API

Use cases

  • Search PubMed for research articles on specific topics with advanced query syntax and filters
  • Retrieve full-text articles from open-access sources (PMC, EPMC, Unpaywall) for literature review
  • Generate formatted citations in multiple styles (APA, MLA, BibTeX, RIS, Vancouver) for bibliography management
  • Find related articles, citing articles, and references to build a comprehensive literature map
  • Resolve partial citations to PubMed IDs and convert between different article identifier types (PMID, PMCID, DOI)

io.github.cyanheads/pubmed-mcp-server MCP server FAQ

What is the pubmed-mcp-server?

It's an MCP server that provides access to PubMed, PubMed Central, and Europe PMC for searching biomedical literature, fetching article metadata and full text, and working with citations and MeSH vocabulary.

Is it free to use?

Yes, the server itself is free and open-source (Apache 2.0). PubMed and Europe PMC are free public databases. An optional NCBI API key increases rate limits from 3 to 10 requests/second.

How do I install it in Claude Desktop or Cursor?

Use the npm package @cyanheads/pubmed-mcp-server via npx or bunx, or connect to the public hosted instance at https://pubmed.caseyjhand.com/mcp using Streamable HTTP. Installation buttons are available in the GitHub repository.

Do I need authentication?

No authentication is required by default. The server supports optional JWT or OAuth modes, but PubMed and Europe PMC are publicly accessible without credentials.

Can I fetch full-text articles?

Yes, via pubmed_fetch_fulltext, which chains NCBI PMC → Europe PMC → Unpaywall. It returns structured full text with section filtering and character budgets. Set UNPAYWALL_EMAIL to enable Unpaywall layer for DOI-based OA resolution.

What data sources does it access?

PubMed (MEDLINE), PubMed Central (PMC), Europe PMC (preprints, patents, Agricola), and Unpaywall (open-access full text). All are free, public biomedical databases.

README (reference)

Source of truth, from the repository.

<div align="center"> <h1>@cyanheads/pubmed-mcp-server</h1> <p><b>Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms via MCP. STDIO or Streamable HTTP.</b> <div>11 Tools • 1 Resource • 1 Prompt</div> </p> </div> <div align="center">

Version License Docker MCP SDK npm TypeScript Bun

</div> <div align="center">

Install in Claude Desktop Install in Cursor Install in VS Code

Framework

</div> <div align="center">

Public Hosted Server: https://pubmed.caseyjhand.com/mcp

</div>

Tools

11 tools for working with PubMed, PubMed Central, and Europe PMC data:

ToolDescription
pubmed_search_articlesSearch PubMed with full query syntax, field-specific filters, date ranges, pagination, and optional brief summaries
pubmed_europepmc_searchSearch Europe PMC for preprints, patents, Agricola, and EPMC-only OA records that don't surface in PubMed. Cursor-based pagination.
pubmed_europepmc_fetchFetch complete Europe PMC records — including the untruncated abstract — by source + epmcId, the only identifier many preprint, patent, and Agricola records carry
pubmed_fetch_articlesFetch full article metadata by PMIDs — abstract, authors, journal, MeSH terms, grants
pubmed_fetch_fulltextFetch full-text articles via a chain: NCBI PMC EFetch → Europe PMC fullTextXML → Unpaywall. Accepts PMIDs, PMCIDs, or DOIs.
pubmed_format_citationsGenerate formatted citations in APA 7th, MLA 9th, BibTeX, RIS, or Vancouver (ICMJE/NLM)
pubmed_find_relatedFind similar articles, citing articles, or references for a given PMID
pubmed_spell_checkSpell-check biomedical queries using NCBI's ESpell service
pubmed_lookup_meshSearch and explore MeSH vocabulary — tree numbers, scope notes, entry terms
pubmed_lookup_citationResolve partial bibliographic references to PubMed IDs via ECitMatch
pubmed_convert_idsConvert between DOI, PMID, and PMCID using the PMC ID Converter API

pubmed_search_articles

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
  • Returns the original query plus the fully applied PubMed query and normalized filter metadata

pubmed_fetch_articles

Fetch full article metadata by PubMed IDs.

  • Batch fetch up to 200 articles at once (auto-switches to POST for batches >= 100)
  • 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_fetch_fulltext

Fetch full-text articles via a three-stage chain: NCBI PMC EFetch → Europe PMC fullTextXML → Unpaywall.

  • Accepts exactly one of pmcids (direct PMC IDs), pmids (PubMed IDs, auto-resolved), or dois (auto-resolved to PMC via the ID Converter; preprints and EPMC-only OA fall through to Europe PMC / Unpaywall)
  • NCBI PMC and Europe PMC both return structured JATS; output records origin via viaSource: "pmc" | "europepmc" | "unpaywall"
  • Europe PMC layer (enabled by default; disable with EUROPEPMC_ENABLED=false) recovers PMC-counterpart records that NCBI PMC EFetch missed, and resolves DOI input to PMC counterparts when one exists. EPMC's fullTextXML is PMC-keyed, so preprints (PPR), patents (PAT), and Agricola (AGR) are reachable via pubmed_europepmc_search for metadata but have no full text via this chain.
  • Unpaywall layer (enabled by setting UNPAYWALL_EMAIL) resolves DOIs to legal OA copies; extracts HTML landing pages to Markdown via Defuddle or PDFs to text via unpdf
  • Discriminated output contract — source: "pmc" (structured sections, regardless of whether it came from PMC or EPMC) or source: "unpaywall" (best-effort body + contentFormat: html-markdown or pdf-text)
  • Structured unavailable reasons (not-found, no-pmc-fallback-disabled, no-epmc-fulltext, no-doi, no-oa, fetch-failed, parse-failed, service-error) so callers can retry or explain to users without parsing text
  • Each unavailable entry carries idType (pmid / pmcid / doi) and triedTiers — per-tier outcomes (not-attempted, miss, no-fulltext, service-error, …) in execution order, so callers can see which stage failed and why
  • Section filtering by title (case-insensitive match, e.g. ["methods", "results"]) and configurable max sections apply to PMC output
  • Character budgets keep context size predictable: maxCharacters caps body text per article (PMC sections and subsections, or the Unpaywall body), maxCharactersPerSection caps a single PMC section, and overflowMode picks between truncate (fill sections in document order) and outline (split the budget evenly so every heading survives with an excerpt). Budgets run after the semantic filters, and a truncation object reports per-article and per-section character counts whenever anything was shortened
  • Up to 10 articles per request

pubmed_europepmc_search

Search Europe PMC (EBI/EMBL-EBI), a broader open-access biomedical corpus than PubMed alone.

  • Surfaces records PubMed search can't reach — preprints (source: PPR), patents (source: PAT), Agricola (source: AGR), plus everything in PubMed (MED) and PMC (PMC). On recent queries this can mean dozens of relevant hits with zero PubMed overlap.
  • Default sources ["MED", "PMC", "PPR"]; pass sources to include PAT / AGR
  • Cursor-based pagination via cursorMark (unlike pubmed_search_articles, which uses offset) — * for the first page, return nextCursorMark for the next
  • Output discriminator on source plus optional pmid / pmcId / doi cross-walking
  • abstractSnippet is capped at 400 characters to keep a page bounded; abstractTruncated says whether it was cut, and pubmed_europepmc_fetch returns the whole abstract for the records worth reading in full
  • Disabled when EUROPEPMC_ENABLED=false; tool is not registered in that case

pubmed_europepmc_fetch

Fetch complete Europe PMC records by source + epmcId, the detail counterpart to pubmed_europepmc_search.

  • Returns the full, untruncated abstract as display-ready plain text — markup stripped, HTML entities decoded
  • Addressed by the source and epmcId of a search hit, the only identifier preprint (PPR), patent (PAT), and Agricola (AGR) records reliably carry — pubmed_fetch_articles needs a PMID and pubmed_fetch_fulltext needs a PMCID, PMID, or DOI
  • Up to 25 records per call, resolved in a single Europe PMC request
  • Pairs unresolved requests back to the caller in notFound instead of failing the batch
  • Disabled when EUROPEPMC_ENABLED=false; tool is not registered in that case

pubmed_format_citations

Generate formatted citations for articles.

  • Five citation styles: APA 7th, MLA 9th, BibTeX, RIS, Vancouver (ICMJE/NLM)
  • Request multiple styles per article in a single call
  • Hand-rolled formatters — zero external dependencies, fully Workers-compatible
  • Up to 50 articles per request
  • Reports formatted counts and unavailable PMIDs for partial-result handling

pubmed_find_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
  • Results returned in NCBI's relevance order

pubmed_spell_check

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_lookup_mesh

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

pubmed_lookup_citation

Resolve partial bibliographic references to PubMed IDs via NCBI ECitMatch.

  • Match citations by journal, year, volume, first page, and/or author name
  • More fields = better match accuracy; at least one field required
  • Batch up to 25 citations per request
  • Deterministic matching — more reliable than free-text search for known references
  • Returns explicit matched, not_found, and ambiguous statuses with recovery detail

pubmed_convert_ids

Convert between article identifiers (DOI, PMID, PMCID) using the PMC ID Converter API.

  • Batch up to 50 IDs per request
  • Accepts DOIs, PMIDs, or PMCIDs (all IDs must be the same type)
  • Only resolves articles indexed in PubMed Central
  • Per-ID success/error reporting — partial batches return resolved mappings alongside structured errors for unresolvable IDs, not a batch-level failure

Resource and prompt

TypeNameDescription
Resourcepubmed://database/infoPubMed database metadata via EInfo (field list, record count, last update)
Promptresearch_planGenerate a structured 4-phase biomedical research plan outline

Features

Built on @cyanheads/mcp-ts-core:

  • Declarative tool definitions — single file per tool, framework handles registration and validation
  • Unified error handling across all tools
  • Pluggable auth (none, jwt, oauth)
  • Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
  • Structured logging with optional OpenTelemetry tracing
  • 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, ECitMatch) plus PMC ID Converter
  • 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, Vancouver) — zero deps, Workers-compatible

Agent-friendly output:

  • Provenance on every response — source labels, license fields, best-effort warnings on Unpaywall results, and effective-query echo on searches so agents can reason about trust
  • Graceful partial failure — batch tools return per-item success/error rows instead of failing the request, with structured status codes and actionable next-step text
  • Discriminated output contracts — source: "pmc" | "unpaywall", typed unavailable reasons, viaSource and triedTiers fields — callers branch on data, not string parsing

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

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "pubmed-mcp-server": {
      "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-mcp-server": {
      "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-mcp-server": {
      "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=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

Installation

  1. Clone the repository:
git clone https://github.com/cyanheads/pubmed-mcp-server.git
  1. Navigate into the directory:
cd pubmed-mcp-server
  1. Install dependencies:
bun install

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Key environment variables:

VariableDescriptionDefault
MCP_TRANSPORT_TYPETransport: stdio or httpstdio
MCP_HTTP_PORTHTTP server port3010
MCP_HTTP_ENDPOINT_PATHHTTP endpoint path where the MCP server is mounted/mcp
MCP_PUBLIC_URLPublic origin override for TLS-terminating reverse-proxy deployments (landing page, Server Card, RFC 9728 metadata).none
MCP_AUTH_MODEAuthentication: none, jwt, or oauthnone
MCP_LOG_LEVELLog level (debug, info, warning, error, etc.)info
MCP_GC_PRESSURE_INTERVAL_MSOpt-in Bun-only forced-GC pressure loop (ms). Drains the per-request McpServer/McpSessionTransport cycle under sustained low-traffic HTTP. Recommended starting point if heap growth is observed: 60000.0 (disabled)
LOGS_DIRDirectory for log files (Node.js only).<project-root>/logs
STORAGE_PROVIDER_TYPEStorage backend: in-memory, filesystem, supabase, cloudflare-kv/r2/d1in-memory
NCBI_API_KEYNCBI API key for higher rate limits (10 req/s vs 3 req/s)none
NCBI_ADMIN_EMAILContact email sent with NCBI requests (recommended by NCBI)none
NCBI_REQUEST_DELAY_MSMinimum gap between NCBI request starts in ms334 (100 with key)
NCBI_MAX_CONCURRENTMax concurrent in-flight NCBI requests8
NCBI_MAX_RETRIESRetry attempts for failed NCBI requests6
NCBI_TIMEOUT_MSPer-request HTTP timeout in ms30000
NCBI_TOTAL_DEADLINE_MSTotal deadline across all retry attempts for one NCBI call, in ms60000
UNPAYWALL_EMAILContact email for Unpaywall. When set, pubmed_fetch_fulltext falls back to Unpaywall open-access copies for non-PMC DOIsnone
UNPAYWALL_TIMEOUT_MSPer-request HTTP timeout for Unpaywall lookups and content fetches, in ms20000
EUROPEPMC_ENABLEDEnable Europe PMC search tool and the pubmed_fetch_fulltext JATS fallback chain. Set false to disable all EPMC calls and skip tool registration.true
EUROPEPMC_EMAILOptional contact email sent with Europe PMC requests (EBI courtesy).none
EUROPEPMC_REQUEST_DELAY_MSMinimum gap between Europe PMC request starts in ms200
EUROPEPMC_MAX_RETRIESRetry attempts for failed Europe PMC requests3
EUROPEPMC_TIMEOUT_MSPer-request HTTP timeout for Europe PMC calls, in ms20000
OTEL_ENABLEDEnable OpenTelemetryfalse

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
    

Project structure

DirectoryPurpose
src/mcp-server/toolsTool definitions (*.tool.ts). Eleven tools across PubMed, PMC, and Europe PMC.
src/mcp-server/resourcesResource definitions. Database info resource.
src/mcp-server/promptsPrompt definitions. Research plan prompt.
src/services/ncbiNCBI E-utilities service layer — API client, queue, parser, formatter.
src/services/europe-pmcEurope PMC service — search + fullTextXML JATS retrieval. Reuses the NCBI JATS parser.
src/services/unpaywallUnpaywall service — DOI → OA location resolution and content fetch (HTML/PDF).
src/configServer-specific environment variable parsing and validation with Zod.
tests/Unit and integration tests, mirroring the src/ structure.

Development guide

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

  • Handlers throw, framework catches — no try/catch in tool logic
  • Use ctx.log for logging, ctx.state for storage
  • Register new tools and resources in the createApp() arrays

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.

Related MCP servers

Countries, timezones, elements, constants, HTTP status codes, unit conversion, and MIME type lookup.

1
TypeScript
Apache-2.0
View repository →

Search ReliefWeb humanitarian reports, disasters, jobs, training, and country profiles via MCP.

1
TypeScript
Apache-2.0
View repository →

Search Austrian federal and state law, court decisions, and the authentic Bundesgesetzblatt (RIS).

2
TypeScript
Apache-2.0
View repository →

Screen names against OFAC, EU, UK, UN sanctions lists; resolve entities via GLEIF. Screening aid.

1
TypeScript
Apache-2.0
View repository →

Query SEC EDGAR filings, XBRL financials, and company data through MCP. STDIO & Streamable HTTP.

6
TypeScript
Apache-2.0
View repository →

Search Jellyseerr/Overseerr, check availability, and create guarded media requests.

1
TypeScript
Apache-2.0
View repository →