What are the system requirements?
Python 3.10+, FastMCP library, and packages: asyncio, logging, requests, beautifulsoup4.
@JackKuo666
Basic information
🔍 Enable AI assistants to search, access, and analyze PubMed articles through a simple MCP interface.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"pubmed": {
"command": "bash",
"args": [
"-c",
"source /home/YOUR/PATH/mcp-server-pubmed/.venv/bin/activate && python /home/YOUR/PATH/pubmed-mcp-server.py"
],
"env": {},
"disabled": false,
"autoApprove": []
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
PubMed MCP Server provides a bridge between AI assistants and PubMed’s biomedical literature repository through the Model Context Protocol (MCP). It enables AI models to search for scientific articles, access metadata, and perform deep analysis programmatically.
Install Python 3.10+, FastMCP, and other dependencies (requests, beautifulsoup4). Clone the repository, run pip install -r requirements.txt, then start the server with python pubmed_server.py. For desktop clients, configure the MCP server JSON (examples for Claude Desktop and Cline are provided). Alternatively, install automatically via Smithery (commands for Claude, Cursor, Windsurf, CLine).
Python 3.10+, FastMCP library, and packages: asyncio, logging, requests, beautifulsoup4.
Clone the repository, install dependencies via `pip install -r requirements.txt`, and run `python pubmed_server.py`. Optionally, install via Smithery for automated client setup.
Five tools: `search_pubmed_key_words`, `search_pubmed_advanced`, `get_pubmed_article_metadata`, `download_pubmed_pdf`, and `deep_paper_analysis`.
The tool `download_pubmed_pdf` attempts to download the full-text PDF for a PubMed article, but availability depends on PubMed’s access policies.
No authentication is mentioned. The server uses public PubMed APIs and respects PubMed’s terms of service.
Hosted YouTube MCP server for search, video metadata, channel data and timestamped transcripts. Connect Claude, Cursor or other MCP clients with HasData; no YouTube API key required.

Extract products, prices, images and reviews from any page in one click — or connect your AI agent and let it do the scraping for you. Works great for: - Ecommerce: extract every product from a Shopify, WooCommerce or

Company search and enrichment for AI agents: 200+ countries of company data from official business registers. Search companies, get full firmographic records and look up exact city names. Hosted MCP, no install.
Query 2,000+ DeFi vaults across 25+ protocols and 14 EVM chains. Get vault risk scores, APR/APY and TVL history, risk-adjusted yield, DeFi base rates and hack/exploit data — for Claude, Cursor, Codex, Gemini CLI and any
Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl
Comments