広告掲載
MCP.so
ログイン

PubMed MCP Server

@chrismannina

リポジトリ

基本情報

カテゴリ

データと分析

ライセンス

MIT

トランスポート

stdio

作者

chrismannina

PubMed MCP Server について

A Model Context Protocol (MCP) server that enables AI assistants to search and analyze PubMed medical literature with advanced filtering, citations, and research tools.

PubMed MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "pubmed-mcp": {
      "command": "python",
      "args": [
        "-m",
        "src.main"
      ]
    }
  }
}

PubMed MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is PubMed MCP Server?

A comprehensive Model Context Protocol (MCP) server for PubMed literature search and management. It provides advanced search capabilities, citation formatting, and research analysis tools, integrating with the PubMed API through NCBI E‑utilities. Designed for researchers, developers, and anyone needing programmatic access to PubMed.

How to use PubMed MCP Server?

Install Python 3.8+, obtain a free NCBI API key and a valid email, clone the repository, install dependencies (pip install -r requirements.txt), configure environment variables in a .env file, then run python -m src.main. Use an MCP client to call tools such as search_pubmed, get_article_details, and export_citations.

Key features of PubMed MCP Server

  • Advanced PubMed search with date ranges, article types, authors, journals, and MeSH terms
  • Retrieve detailed article information including abstracts, authors, and metadata
  • Export citations in BibTeX, APA, MLA, Chicago, Vancouver, EndNote, and RIS formats
  • Search by author with co‑author information
  • Discover related articles and explore MeSH terms
  • Analyze publication trends over time and compare multiple articles
  • Built‑in caching and configurable rate limiting for respectful API usage

Use cases of PubMed MCP Server

  • Automate literature searches with complex filters for systematic reviews
  • Fetch and format citations for reference management tools
  • Analyze research trends by topic over a specified number of years
  • Compare multiple articles side‑by‑side for literature analysis
  • Integrate PubMed search capabilities into AI assistants and research workflows

よくある質問

1

What API key is required?

A free NCBI API key is required. Obtain it from NCBI Account Settings under “API Key Management”.

2

What are the runtime dependencies?

Python 3.8 or higher, an NCBI API key, and a valid email for NCBI API identification.

3

Does the server store any data locally?

It uses built‑in caching (configurable TTL and max size) for improved performance, but no persistent storage of user data is described.

4

Are there any rate limits?

The server includes configurable rate limiting to ensure respectful API usage. The default rate limit parameter is `RATE_LIMIT=3.0`.

5

Can I run the server in a container?

Yes, a Dockerfile and Docker Compose configuration are provided. Build with `make docker-build` and run with `make docker-run` or via `docker-compose`.

コメント

「データと分析」の他のコンテンツ

SocialAPIs — Facebook & Instagram Data

SocialAPIsHub

Facebook & Instagram data for AI agents — pages, posts, groups, Ads Library, Marketplace, profiles and reels. 47 read-only tools with structured output.

1

Manifold MCP

Jesse Sibley

An MCP for marketers that gives agents tools for SEO, AEO, socials and ads data. Generous free tier; works in Claude, ChatGPT, Cursor and other MCP clients.

OrbitWan.io

Wanchain explorer data and analytics: addresses, transactions, tokens, validators, cross chain transfers, plus OrbitPay prepaid premium data (x402).

Lawstronaut Legal Research

Lawstronaut-FZCO

Connect your AI to millions of laws and court cases! Lawstronaut is the infrastructure layer that connects AI agents and software to millions of legal documents across 150+ jurisdictions, structured legal data, continuou

1

Midpoint Card Prices

I Lov Guitars Inc.

Trading-card market prices and grading ROI as MCP tools. Read-only, no auth. Powers the Midpoint Card Prices plugin in ChatGPT; works with Claude, Cursor and any MCP client.

広告掲載