MCP server for the NCBI E-utilities API. Search PubMed, fetch article metadata and full text, generate citations, explore MeSH terms, and discover related research.
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
tools
-
pubmed_convert_ids
Convert between article identifiers (DOI, PMID, PMCID). Accepts up to 50 IDs of a single type per request. Uses the NCBI PMC ID Converter API — only resolves articles indexed in PubMed Central. For articles not in PMC, use pubmed_search_articles instead.
in ▸ ids idtype
-
pubmed_fetch_articles
Fetch full article metadata by PubMed IDs. Returns detailed article information including abstract, authors, journal, MeSH terms.
in ▸ pmids includeMesh includeGrants
-
pubmed_fetch_fulltext
Fetch full-text articles from PubMed Central (PMC). Returns complete article body text, sections, and references for open-access articles. Accepts PMC IDs directly or PubMed IDs (auto-resolved via ELink).
in ▸ pmids pmcids sections maxSections includeReferences
-
pubmed_find_related
Find articles related to a source article — similar content, citing articles, or references.
in ▸ pmid maxResults relationship
-
pubmed_format_citations
Get formatted citations for PubMed articles in APA, MLA, BibTeX, or RIS format.
in ▸ pmids styles
-
pubmed_lookup_citation
Look up PubMed IDs from partial bibliographic citations. Useful when you have a reference (journal, year, volume, page, author) and need the PMID. Uses NCBI ECitMatch for deterministic matching — more reliable than searching by citation fields.
in ▸ citations
-
pubmed_lookup_mesh
Search and explore MeSH (Medical Subject Headings) vocabulary. Essential for building precise PubMed queries.
in ▸ term maxResults includeDetails
-
pubmed_search_articles
Search PubMed with full query syntax, filters, and date ranges. Returns PMIDs and optional brief summaries. Supports field-specific filters (author, journal, MeSH terms), common filters (language, species, free full text), and pagination via offset for paging through large result sets.
in ▸ sort query author offset journal species language dateRange meshTerms maxResults hasAbstract freeFullText summaryCount publicationTypes
-
pubmed_spell_check
Spell-check a query and get NCBI's suggested correction. Useful for refining search queries.
in ▸ query
resources
- database-info PubMed database metadata including field list, last update date, and record count.
prompts
- research_plan Generate a structured research plan outline for a biomedical research project.
analyzed v2.9.5 · analyzer v17 · 1h ago
skills & prompt files 2
- agent-rulespackage/AGENTS.md
- agent-rulespackage/CLAUDE.md
network 3
- net package/dist/mcp-server/tools/definitions/fetch-fulltext.tool.js :283
.describe('PMC IDs to fetch (e.g. ["PMC9575052"]). Provide exactly one of `pmcids`, `pmids`, or `dois`.'), - net package/dist/services/ncbi/api-client.js :55
* Uses plain fetch (not fetchWithTimeout) so we can capture response bodies on - net package/dist/services/ncbi/ncbi-service.js :327
* and the HTTP fetch (cancels wedged requests).
declared dependencies 18
- @cyanheads/mcp-ts-core@^0.10.6
- defuddle@^0.18.1
- fast-xml-parser@^5.8.0
- linkedom@^0.18.12
- pino-pretty@^13.1.3
- sanitize-html@^2.17.5
- unpdf@^1.6.2
- zod@^4.4.3
- @biomejs/biome@^2.5.0
- @types/node@^25.9.3
- @types/sanitize-html@^2.16.1
- @vitest/coverage-istanbul@^4.1.8
- depcheck@^1.4.7
- fast-check@^4.8.0
- ignore@^7.0.5
- tsc-alias@^1.8.17
- typescript@^6.0.3
- vitest@^4.1.8