PubMed MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NCBI_API_KEY | No | Optional NCBI API key to increase rate limit from 3 req/s to 10 req/s. Obtain from NCBI account settings. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchA | Search PubMed with MeSH support, structured filters, pagination, and selectable output verbosity. output_mode=minimal returns id/title/url/full_text_available only (legacy-compatible); compact (default) adds authors/journal/year/doi/pmcid; full additionally includes abstract/mesh_terms/publication_types. |
| fetchA | Retrieve abstract for a single PMID (OpenAI MCP compliant). Accepts exactly one PMID. For multiple PMIDs, use fetch_batch. |
| fetch_batchA | Retrieve abstracts for multiple PMIDs in a single batch request. Returns structured data per PMID. Set include_abstract=false to omit the abstract field (e.g., when you only need full author lists). |
| get_full_textA | Retrieve full text of articles from PubMed Central (PMC) by PMC ID. Supports section filtering to reduce token usage. |
| countA | Get only the count of search results for query adjustment and optimization. Fast — retrieves no actual data. Useful for refining search strategies. |
| find_similar_articlesA | Find similar articles for a given PMID using MeSH terms and title-based similarity. Useful for literature review and related research discovery. |
| export_to_risA | Export PubMed articles to RIS format for citation managers (EndNote/Zotero/Mendeley). Returns compact RIS with minimal metadata — citation managers auto-fetch the rest via PMID. |
| get_citation_countsA | Get citation counts for PMIDs. Default source is iCite (counts only, includes citations from outside PubMed). Set citing_source='pubmed' for elink-based PubMed-internal citations and to retrieve citing PMIDs (useful for backward snowballing). |
| convert_idsA | Convert between PMID, PMCID, and DOI identifiers using NCBI ID Converter API. |
| batch_processA | Run multiple operations against the same set of PMIDs in one call. Helpful for systematic-review style workflows. operations is an array drawn from: 'abstract', 'citations', 'similar', 'ris_export', 'full_text'. Respects NCBI rate limits via max_concurrency (default 3). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool serves a distinct purpose: search, abstract retrieval (single/batch), full-text, count, similarity, export, citations, ID conversion, and batch processing. Overlapping tools like fetch/fetch_batch and search/count are clearly differentiated by scope and description.
All tool names use lowercase snake_case and follow a predictable verb-first pattern (e.g., search, fetch, get_full_text, export_to_ris). The naming style is consistent and readable across the entire set.
10 tools is well-scoped for a PubMed server, covering essential operations without redundancy. Each tool adds meaningful functionality, and the count feels appropriate for the domain.
The tool set covers the full research workflow: search, retrieval, full-text access, counting, similarity discovery, citation analysis, ID conversion, citation export, and batch processing. There are no obvious dead ends or missing core operations for a read-only biomedical literature server.