PubMedSearch MCP Server
@gradusnikov
PubMedSearch MCP Server について
A Model Content Protocol server that provides tools to search and retrieve academic papers from PubMed database.
基本情報
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-search-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@gradusnikov/pubmed-search-mcp-server",
"--client",
"claude"
]
}
}
}ツール
ツールは検出されませんでした
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 PubMedSearch MCP Server?
PubMedSearch MCP Server is a Model Context Protocol server that provides tools to search and retrieve academic papers from the PubMed database. It is intended for users who want to integrate PubMed paper searches into MCP-compatible applications like Claude Desktop.
How to use PubMedSearch MCP Server?
Install via Smithery using npx -y @smithery/cli install @gradusnikov/pubmed-search-mcp-server --client claude, or manually by cloning the repository, installing dependencies (pip install fastmcp requests python-dotenv), and creating an optional .env file. Start the server in development mode with mcp dev pubmed_search_mcp_server.py or add it to the Claude Desktop configuration file.
Key features of PubMedSearch MCP Server
- Search PubMed by keywords in title/abstract or author names
- Retrieve detailed information including title, authors, journal, abstract, DOI and more
- Installable via Smithery for automatic Claude Desktop setup
- Manual installation with Python dependencies and optional configuration
- Runs as a FastMCP server using the
mcpcommand
Use cases of PubMedSearch MCP Server
- Quickly look up recent academic papers on a specific topic
- Retrieve abstracts and DOIs for literature reviews
- Search for papers by known author names
- Integrate PubMed searching into AI assistants like Claude Desktop
FAQ from PubMedSearch MCP Server
What does PubMedSearch MCP Server do?
It provides MCP tools to search and retrieve academic papers from the PubMed database by keywords in title/abstract or author names, returning details like title, authors, journal, abstract, and DOI.
What dependencies are required?
Manual installation requires fastmcp, requests, and python-dotenv, installed via pip.
How do I install it on Claude Desktop automatically?
Use Smithery: run npx -y @smithery/cli install @gradusnikov/pubmed-search-mcp-server --client claude.
Can I run it outside of Claude Desktop?
Yes, start the server in development mode with mcp dev pubmed_search_mcp_server.py from the project root.
Does it require any authentication or API key?
The README does not mention authentication; an optional .env file is noted for configuration but no keys are specified.
「検索」の他のコンテンツ
mcp-omnisearch
spences10🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.
Kagi MCP server
kagisearchThe Official Model Context Protocol (MCP) server for Kagi Search & other tools.
Google Search Tool
web-agent-masterA Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.
Version 2.0 is here!!
mixelpixxMCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites
コメント