PubMed MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for Streamable HTTP mode. Default is 8745. | 8745 |
| PUBMED_EMAIL | No | Optional email address (recommended) to include in requests to NCBI. | |
| ABSTRACT_MODE | No | Abstract length: quick (1500 characters) or deep (6000 characters). | quick |
| FULLTEXT_MODE | No | Full-text download mode: disabled, enabled, or auto. | disabled |
| PUBMED_API_KEY | No | Optional NCBI API key for higher rate limits. https://www.ncbi.nlm.nih.gov/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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pubmed_searchA | Search PubMed biomedical literature database. Returns articles matching your query with metadata, abstracts, and citations. Supports Boolean operators (AND, OR, NOT), MeSH terms, and field tags like [Title], [Author]. Use format="compact" for quick overviews when browsing, "detailed" for in-depth analysis. Use days_back to limit to recent publications. |
| pubmed_get_detailsA | Retrieve complete metadata for specific PubMed articles by PMID. Accepts a single PMID or array of PMIDs (up to 20). Returns full article records including abstract, authors, journal, DOI, MeSH terms. Use when you have specific PMIDs from a previous search or citation and need the full record. |
| pubmed_extract_infoA | Extract specific structured sections from a PubMed article. Use when you need only certain aspects (author details, structured abstract, keywords, DOI) rather than the full record. More token-efficient than get_details for targeted extraction. |
| pubmed_find_relatedA | Find articles related to a given PubMed article. Discovers similar papers or review articles to build a comprehensive literature picture. Use after identifying a key paper to expand your search in relevant directions. |
| pubmed_manage_cacheA | View cache statistics or perform maintenance. Use action="stats" to check hit rates and storage usage. Use action="clean" to remove expired entries, or action="clear" to wipe a specific cache layer. |
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 5 tools
Most tools have clearly distinct roles: search, related-article discovery, full-record retrieval, targeted extraction, and cache maintenance. However, pubmed_get_details and pubmed_extract_info both operate on specific articles and could be confused, though the descriptions clarify that get_details is for full records and extract_info is for targeted sections.
All tool names follow a consistent pattern with the 'pubmed_' prefix followed by a verb phrase: search, find_related, get_details, extract_info, manage_cache. The naming convention is uniform, readable, and makes the action of each tool predictable.
Five tools is well-scoped for a PubMed literature search and retrieval server. Each tool has a clear purpose, and the count is neither too thin nor overwhelming for the domain.
The server covers the core PubMed workflow: searching, finding related papers, retrieving full details, and extracting specific sections. Minor gaps exist such as citation formatting or advanced query helpers, but these are not essential for the primary search-and-retrieval use case.