Ncbi MCP Server

A Model Context Protocol (MCP) server for searching NCBI databases, designed for researchers across all life sciences and biomedical fields. This

Local serverstdioPython

What is the Ncbi MCP server?

Ncbi mcp server connects Ncbi to AI assistants that speak the Model Context Protocol. A Model Context Protocol (MCP) server for searching NCBI databases, designed for researchers across all life sciences and biomedical fields. This server provides seamless access to PubMed's vast collection of 35+ million scientific articles through natural language queries, enabling AI assistants.

What Ncbi does

A Model Context Protocol (MCP) server for searching NCBI databases, designed for researchers across all life sciences and biomedical fields. This server provides seamless access to PubMed's vast collection of 35+ million scientific articles through natural language queries, enabling AI assistants to help with literature reviews, research discovery, and scientific analysis.

Tools it exposes

Once connected, the assistant can call these 10 tools directly:

  • Prerequisites — The Prerequisites tool exposed by this server
  • search_pubmed — Primary search tool for PubMed database - query: Search terms (supports field tags like [ti] for title, [au] for author, [mh] for MeSH terms) -
  • get_article_details — Fetch complete information for specific articles - pmids: List of PubMed IDs (up to 50)
  • search_mesh_terms — Find standardized Medical Subject Headings - term: Term to search in MeSH database
  • get_related_articles — Discover articles related to a specific paper - pmid: PubMed ID of reference article - max_results: Number of related articles (1-50, default: 10)
  • advanced_search — Complex searches with multiple criteria - terms: List of search terms to combine - operator: "AND", "OR", or "NOT" to combine terms - authors: List
  • get_analytics_summary — Get comprehensive analytics overview "Show me my research analytics summary" Returns: - Total requests and uptime - Operation breakdown (searches, fetches
  • get_detailed_metrics — Detailed performance metrics for specific time periods "Get detailed metrics for the last 24 hours" - hours: Time period to analyze (default: 24) -
  • reset_analytics — Reset analytics data (use with caution) "Reset all analytics data" Note: This permanently clears all collected metrics
  • Monitoring — The Monitoring tool exposed by this server

Installing the ncbi mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Requirements

Where it fits

Database servers turn schema archaeology and ad-hoc reporting into conversation, which is why they tend to be the second or third server people install. Ncbi sits in that group, and the shape of its toolset — Prerequisites, search_pubmed, get_article_details among others — tells you what it is really for. Worth comparing against the other databases servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • With 10 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Ncbi.
  • Maintained by vitorpavinato, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the ncbi mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
PrerequisitesThe Prerequisites tool exposed by this server.
search_pubmedPrimary search tool for PubMed database - **query**: Search terms (supports field tags like [ti] for title, [au] for author, [mh] for MeSH terms) - **max_results**: Number of results (1-100, default: 20) - **sort**: Sort
get_article_detailsFetch complete information for specific articles - **pmids**: List of PubMed IDs (up to 50)
search_mesh_termsFind standardized Medical Subject Headings - **term**: Term to search in MeSH database
get_related_articlesDiscover articles related to a specific paper - **pmid**: PubMed ID of reference article - **max_results**: Number of related articles (1-50, default: 10)
advanced_searchComplex searches with multiple criteria - **terms**: List of search terms to combine - **operator**: "AND", "OR", or "NOT" to combine terms - **authors**: List of author names - **journals**: List of journal names - **pu
get_analytics_summaryGet comprehensive analytics overview "Show me my research analytics summary" Returns: - Total requests and uptime - Operation breakdown (searches, fetches, etc.) - Cache performance metrics - Recent activity and error ra
get_detailed_metricsDetailed performance metrics for specific time periods "Get detailed metrics for the last 24 hours" - **hours**: Time period to analyze (default: 24) - Operation-specific performance data - Timeline analysis with hourly
reset_analyticsReset analytics data (use with caution) "Reset all analytics data" **Note**: This permanently clears all collected metrics.
MonitoringThe Monitoring tool exposed by this server.

Configuration

Example prompts to try

  • Use Ncbi to Prerequisites.
  • Use Ncbi to search pubmed.
  • Use Ncbi to get article details.

Frequently asked questions

It connects Ncbi to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Prerequisites, search_pubmed, get_article_details, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Ncbi directly.