Official Hugging Face MCP server: search models, datasets, Spaces and papers on the Hub, read repository files, and call Gradio apps as agent tools.
PubMed
Summary
Search PubMed's biomedical literature and read abstracts and open-access full text from an AI client.
Features
- Search PubMed's biomedical literature index
- Retrieve abstracts and structured metadata
- Access open-access full text where available
Installation
Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.
Description
This MCP server connects an assistant to PubMed through the NCBI Entrez API, giving it access to the primary index of biomedical and life sciences literature.
What it provides
- Search across PubMed's index using its query syntax, including MeSH terms, field tags, and date filters
- Abstracts and metadata — authors, journal, publication date, DOI, and identifiers
- Full text for open-access articles available through PubMed Central
Where it is useful
Grounding health-related questions in the actual literature rather than in a model's recollection of it, which is a meaningful difference when the topic is clinical. It is equally useful for researchers doing background reading, checking whether a finding has been replicated, or assembling references.
An important caveat
Search results are not clinical guidance, and an assistant summarising abstracts is not a clinician. This is a literature access tool: it makes the evidence findable, and evaluating that evidence remains a human task with the appropriate expertise.
Setup
NCBI asks that requests identify a contact email, supplied through an environment variable. An API key raises the rate limit but is not required. Installed with uvx mcp-simple-pubmed.
Related MCP Servers
Apify's official MCP server — turn thousands of ready-made scrapers into tools your assistant can call.
Browserbase's official MCP server — cloud browser automation with Stagehand's natural-language actions.
Private, self-hosted web search for AI assistants via SearXNG, with pagination, filters, and URL-to-markdown reading.