PubMed
Analyzes PubMed medical literature to help researchers quickly gain insights into medical research dynamics, with features including literature retrieval, hotspot analysis, trend tracking, and comprehensive reports.
What is PubMed?
PubMed is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to analyzes pubmed medical literature to help researchers quickly gain insights into medical research dynamics, with features including literature retrieval, hotspot analysis, trend tracking, and compreh...
Analyzes PubMed medical literature to help researchers quickly gain insights into medical research dynamics, with features including literature retrieval, hotspot analysis, trend tracking, and comprehensive reports.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- fetch_pubmed_content
- generate_pubmed_chart
- get_pubmed_article_connections
- pubmed_research_agent
- search_pubmed_articles
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @cyanheads/pubmed-mcp-serverManual Installation
npx -y @cyanheads/pubmed-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use PubMed
The PubMed MCP server connects AI assistants to the NCBI PubMed database, enabling deep analysis of biomedical literature through NCBI E-Utilities and Europe PMC APIs. It lets researchers search millions of articles, identify research hotspots and publication trends, retrieve full-text connections between papers, and generate comprehensive analysis reports — all through natural language. Researchers and clinicians use it to rapidly synthesize evidence, track emerging topics, and understand the landscape of any biomedical field without manually querying PubMed's web interface.
Prerequisites
- Python 3.10+ and uv package manager installed
- NCBI account with a registered email address (required for API access)
- NCBI API key from https://www.ncbi.nlm.nih.gov/account/ (strongly recommended to avoid rate limits)
- Git to clone the repository
- An MCP client such as Claude Desktop or Claude Code
Clone the repository
Clone the pubmearch repository from GitHub to your local machine.
git clone https://github.com/Darkroaster/pubmearch.git
cd pubmearchCreate and activate a virtual environment
Use uv to create an isolated Python environment and install dependencies from the project.
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv pip install -e .Set required environment variables
Export your NCBI email and API key. The email is required by NCBI policy; the API key raises the rate limit from 3 to 10 requests per second.
export NCBI_USER_EMAIL="[email protected]"
export NCBI_USER_API_KEY="your_ncbi_api_key_here"Verify the server starts correctly
Run the server manually to confirm it starts without errors before adding it to your MCP client. Logs are written to pubmed_server.log and results to pubmearch/results/.
uv run python -m pubmearchAdd to your MCP client configuration
Register the server in your MCP client config file so it launches automatically. Use the absolute path to the project directory and your uv binary.
{
"mcpServers": {
"pubmed": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/pubmearch", "python", "-m", "pubmearch"],
"env": {
"NCBI_USER_EMAIL": "[email protected]",
"NCBI_USER_API_KEY": "your_ncbi_api_key_here"
}
}
}
}PubMed Examples
Client configuration
Example claude_desktop_config.json entry for the PubMed MCP server using uv.
{
"mcpServers": {
"pubmed": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/pubmearch", "python", "-m", "pubmearch"],
"env": {
"NCBI_USER_EMAIL": "[email protected]",
"NCBI_USER_API_KEY": "your_ncbi_api_key_here"
}
}
}
}Prompts to try
Sample requests that exercise the server's search, trend analysis, and report tools.
- "Search PubMed for articles on prostate cancer immunotherapy published in the last 3 months and identify the top research hotspots."
- "Analyze publication count trends for CRISPR gene editing from 2015 to 2024."
- "Find articles related to PMID 38234567, including papers that cite it and papers it references."
- "Generate a comprehensive analysis report on mRNA vaccine research, covering keywords, publication counts, and key findings."Troubleshooting PubMed
HTTP 429 Too Many Requests errors when searching PubMed
Ensure NCBI_USER_API_KEY is set. Without an API key, NCBI limits requests to 3 per second. With a key, the limit rises to 10 per second. Register at https://www.ncbi.nlm.nih.gov/account/ to obtain a key.
Server exits immediately with an error about missing environment variables
Make sure NCBI_USER_EMAIL and NCBI_USER_API_KEY are set either in your shell before launching or in the env block of your MCP client config. Both must be non-empty strings.
No results returned for a valid search query
PubMed requires proper boolean syntax. Use field tags such as [Title/Abstract] and operators like AND/OR. Example: ((cancer[Title/Abstract]) AND (immunotherapy[Title/Abstract])). Avoid plain free-text queries without field qualifiers.
Frequently Asked Questions about PubMed
What is PubMed?
PubMed is a Model Context Protocol (MCP) server that analyzes pubmed medical literature to help researchers quickly gain insights into medical research dynamics, with features including literature retrieval, hotspot analysis, trend tracking, and comprehensive reports. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install PubMed?
Install via npm with the command: npx -y @cyanheads/pubmed-mcp-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with PubMed?
PubMed works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is PubMed free to use?
Yes, PubMed is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
PubMed Alternatives — Similar Data Science & ML Servers
Looking for alternatives to PubMed? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up PubMed in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use PubMed?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.