Search NCBI databases, including PubMed, for scientific literature. Tailored for researchers in life sciences, evolutionary biology, and computational biology.
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.
š¬ Comprehensive Search: Search PubMed's 35+ million articles across all biological disciplines
š Advanced Queries: Support for complex searches with boolean operators, field tags, and filters
š§¬ Life Sciences Research: Covers all biological and biomedical fields including genetics, ecology, medicine, and biotechnology
š» Computational Biology: Perfect for finding bioinformatics methods, algorithms, and computational tools
š¬ Research Applications: Literature reviews, hypothesis generation, method discovery, and staying current with scientific advances
š Full Article Details: Get abstracts, author lists, MeSH terms, DOIs, and publication information
š Related Articles: Discover relevant research through NCBI's relationship algorithms
š MeSH Integration: Search and utilize Medical Subject Headings for precise terminology
Create and initialize project
mkdir ncbi-mcp-server && cd ncbi-mcp-server
poetry init
During init, add dependencies: mcp, httpx, typing-extensions
Create project structure
mkdir -p src/ncbi_mcp_server
# Save server.py code as src/ncbi_mcp_server/server.py
Install dependencies
poetry install
Test the server
poetry run python src/ncbi_mcp_server/server.py
Configure Claude Desktop
Edit your Claude Desktop config file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%/Claude/claude_desktop_config.json~/.config/claude/claude_desktop_config.jsonAdd this configuration:
{
"mcpServers": {
"ncbi-literature": {
"command": "poetry",
"args": ["run", "python", "src/ncbi_mcp_server/server.py"],
"cwd": "/FULL/PATH/TO/YOUR/ncbi-mcp-server"
}
}
}
Restart Claude Desktop and start searching!
conda env create -f environment.yml
conda activate ncbi-mcp
python server.py
python -m venv venv
source venv/bin/activate # Linux/macOS
pip install -r requirements.txt
python server.py
Search for phylogenetic studies:
"Search for recent phylogenetic analysis papers on mammalian evolution"
ā Uses: search_pubmed with query "phylogenetic analysis[ti] AND mammalian[ti] AND evolution"
Find computational phylogenetics methods:
"Find papers about maximum likelihood methods for phylogenetic reconstruction"
ā Uses: search_pubmed with query "maximum likelihood[ti] AND phylogenetic reconstruction"
Search by specific organism:
"Find recent papers on Drosophila comparative genomics"
ā Uses: search_pubmed with query "Drosophila[ti] AND comparative genomics[ti]"
Algorithm and method papers:
"Search for machine learning applications in genomics from the last 2 years"
ā Uses: search_pubmed with date_range="730" and query "machine learning AND genomics"
Software and database papers:
"Find papers about new bioinformatics tools for sequence analysis"
ā Uses: search_pubmed with query "bioinformatics[ti] AND software[ti] AND sequence analysis"
Multi-criteria search:
"Find review articles about CRISPR applications in evolutionary studies published in Nature or Science"
ā Uses: advanced_search with terms=["CRISPR", "evolution"], publication_types=["Review"], journals=["Nature", "Science"]
Author-specific searches:
"Find recent papers by researchers working on ancient DNA and phylogenomics"
ā Uses: search_pubmed with query "ancient DNA[ti] AND phylogenomics[ti]"
search_pubmedPrimary search tool for PubMed database
[ti] for title, [au] for author, [mh] for MeSH terms)Examples:
"CRISPR[ti] AND evolution" - CRISPR in title AND evolution anywhere"phylogenetic analysis[mh]" - Using MeSH term for phylogenetic analysis"computational biology AND machine learning" - Boolean searchget_article_detailsFetch complete information for specific articles
Returns full abstracts, author lists, MeSH terms, DOI, publication details
search_mesh_termsFind standardized Medical Subject Headings
Helps discover related concepts and improve search precision
get_related_articlesDiscover articles related to a specific paper
Perfect for literature reviews and finding relevant research
advanced_searchComplex searches with multiple criteria
The NCBI MCP Server includes comprehensive analytics to help you understand your research patterns and optimize performance.
get_analytics_summaryGet comprehensive analytics overview
"Show me my research analytics summary"
Returns:
get_detailed_metricsDetailed performance metrics for specific time periods
"Get detailed metrics for the last 24 hours"
reset_analyticsReset analytics data (use with caution)
"Reset all analytics data"
Note: This permanently clears all collected metrics.
Usage Patterns:
Performance Metrics:
Research Insights:
Configure credentials:
cp .env.example .env
# Edit .env with your NCBI email and API key
Choose deployment method:
# Local development
./deploy.sh local
# Docker deployment
./deploy.sh docker
# Production deployment
./deploy.sh production
Perfect for development and testing:
poetry install
poetry run python -m src.ncbi_mcp_server.server
Recommended for most users with two options:
Full setup with Redis (recommended):
# Copy and configure environment
cp .env.example .env
# Edit .env with your NCBI email and API key
# Start all services
docker-compose up -d
Simple setup without Redis:
# For basic usage without Redis dependencies
cp .env.example .env
# Edit .env with your NCBI email
docker-compose -f docker-compose.simple.yml up -d
Full setup includes:
Simple setup includes:
For production environments:
# Configure production settings
cp .env.production .env
# Edit with production values
# Deploy
./deploy.sh production
Docker logs:
docker-compose logs -f ncbi-mcp-server
Cache monitoring:
cache_stats()Health checks:
# Test server health
curl http://localhost:8000/health
# Test via MCP
python -c "from src.ncbi_mcp_server.server import cache_stats; import asyncio; print(asyncio.run(cache_stats()))"
For higher rate limits and better performance:
src/ncbi_mcp_server/server.py:# Replace the line: ncbi_client = NCBIClient()
# With:
ncbi_client = NCBIClient(
email="your.email@university.edu",
api_key="your_api_key_here"
)
poetry shell # Activate virtual environment
poetry add package # Add new dependency
poetry remove package # Remove dependency
poetry update # Update all dependencies
poetry run python ... # Run commands in environment
poetry build # Create distribution packages
poetry add --group dev black mypy pytest isort flake8
poetry run black . # Format code
poetry run mypy . # Type checking
poetry run pytest # Run tests
poetry run isort . # Sort imports
# They just need:
git clone your-repo
cd ncbi-mcp-server
poetry install
# Everything works identically!
PubMed supports many field tags for precise searching:
[ti] - Title[tiab] - Title and Abstract[au] - Author[mh] - MeSH Terms[journal] - Journal Name[pdat] - Publication Date[pt] - Publication Type[lang] - Language[sb] - Subset (e.g., medline, pubmed)Example Advanced Queries:
"machine learning"[ti] AND "phylogen*"[tiab] AND "2020"[pdat]:"2024"[pdat]
evolutionary[mh] AND computational[ti] AND (genomics[tiab] OR proteomics[tiab])
"ancient DNA"[ti] AND (paleogenomics[mh] OR phylogenomics[tiab])
search_pubmed("computational phylogenetics")search_mesh_terms("phylogenetics")get_related_articles(pmid="key_paper_id")get_article_details(pmids=["12345", "67890"])search_pubmed("new methods", date_range="90")search_pubmed("author_name[au]", sort="pub_date")advanced_search with your research keywordssearch_pubmed("algorithm[ti] AND your_field")search_pubmed("software[ti] OR tool[ti] AND bioinformatics")search_pubmed("comparison[ti] OR benchmark[ti]")Server won't start:
pip install -r requirements.txtNo search results:
Rate limit errors:
XML parsing errors:
This MCP server is designed to grow with the research community. Ideas for enhancement:
This project is open source. Feel free to modify and distribute according to your institution's policies.
Perfect for researchers in:
Start exploring the vast world of biological literature with powerful, precise searches!
Enables LLMs to search, download, and extract information from YouTube music videos.
Provides comprehensive patent search and statistical analysis for intelligence analysis, technological innovation, and intellectual property management.
A comprehensive search API for real-time web search, data extraction, and crawling, requiring a Tavily API key.
Web search and webpage scraping using the Serper API.
Enhances LLM responses with factual, real-time web content using Jina AI's grounding capabilities.
Search and retrieve content from the Unsloth AI documentation.
Access step-by-step drawing tutorials and guides from easydrawingguides.com for artists of all skill levels.
A server for Brave Search, enabling web search capabilities via its API.
An MCP server for web and similarity search, designed for Claude Desktop. It integrates with various external embedding and API services.
MCP server for interacting with the Ordiscan API to query Bitcoin ordinals and inscriptions. Requires an Ordiscan API key.