gwas-mcp
Provides AI-powered access to major biological databases for GWAS and bioinformatics research. Enables natural language queries for protein, gene, variant, pathway, and drug discovery analysis.
README
🧬 GWAS-MCP: Bioinformatics MCP Server
<!-- mcp-name: io.github.zaeyasa/gwas-mcp -->
A powerful Model Context Protocol (MCP) server for GWAS and bioinformatics research. Seamlessly integrates with Claude Desktop and other MCP clients to provide AI-powered access to major biological databases.
<p align="center"> <img src="https://img.shields.io/badge/Tools-30+-green" alt="30+ Tools"> <img src="https://img.shields.io/badge/Databases-12+-blue" alt="12+ Databases"> <img src="https://img.shields.io/badge/Python-3.10+-blue" alt="Python 3.10+"> </p>
✨ Features
🔬 Protein & Gene Lookup
- UniProt - Search proteins by name, gene, or ID
- Ensembl - Gene information and variant details
- NCBI Gene - Comprehensive gene database
🧪 Clinical & Variants
- ClinVar - Clinical variant interpretations (pathogenic/benign)
- GWAS Catalog - Genome-wide association studies
- GTEx - Expression quantitative trait loci (eQTL)
🔗 Protein Interactions & Networks
- STRING - Protein-protein interactions
- InterPro - Protein domains and families
🏗️ Structures & Pathways
- AlphaFold - AI-predicted protein structures
- PDB - Experimental 3D structures
- KEGG - Metabolic and signaling pathways
💊 Drug Discovery
- Open Targets - Drug target validation & disease associations
- PharmGKB - Pharmacogenomics & drug-gene interactions
🏥 Genetic Diseases
- OMIM - Online Mendelian Inheritance in Man
🚀 Quick Start
Installation
pip install gwas-mcp
Claude Desktop Configuration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"gwas-bioinformatics": {
"command": "python",
"args": ["-m", "gwas_mcp.server"]
}
}
}
Config file location:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Restart Claude Desktop
After adding the configuration, restart Claude Desktop to load the MCP server.
🛠️ Available Tools
Protein & Gene Tools
| Tool | Description |
|---|---|
search_uniprot |
Search UniProt by protein name, gene, or ID |
get_protein_details |
Get detailed protein info (function, domains, GO terms) |
search_ncbi_gene |
Search NCBI Gene database |
search_ensembl_gene |
Get gene location and details from Ensembl |
get_variant_info |
Get SNP/variant info by rsID |
get_interpro_domains |
Get protein domain information |
Clinical & Variant Tools
| Tool | Description |
|---|---|
search_clinvar |
Search ClinVar for clinical variants |
get_clinvar_variant |
Get clinical interpretation for a variant |
annotate_snps |
Annotate SNPs with functional consequences |
query_gwas_catalog |
Query GWAS Catalog for associations |
get_eqtl_data |
Get eQTL data from GTEx |
Protein Interaction Tools
| Tool | Description |
|---|---|
get_protein_interactions |
Find interacting proteins (STRING) |
get_interaction_network |
Get network between multiple proteins |
get_functional_enrichment |
Pathway/GO enrichment analysis |
Structure & Pathway Tools
| Tool | Description |
|---|---|
get_alphafold_structure |
Get AI-predicted structure |
search_alphafold |
Search AlphaFold database |
search_pdb_structures |
Search PDB for 3D structures |
get_pdb_structure |
Get PDB structure details |
search_kegg_pathway |
Search KEGG pathways |
get_kegg_pathway |
Get pathway genes and details |
get_gene_pathways |
Find pathways for a gene |
Drug Discovery Tools
| Tool | Description |
|---|---|
get_drug_targets |
Find drugs targeting a gene (Open Targets) |
get_disease_associations |
Get disease associations with scores |
search_open_targets |
Search genes, diseases, or drugs |
search_pharmgkb |
Search PharmGKB database |
get_drug_gene_interactions |
Get drug-gene interactions |
Genetic Disease Tools
| Tool | Description |
|---|---|
search_omim |
Search OMIM for genetic diseases |
get_gene_diseases |
Get all diseases for a gene |
💬 Example Prompts
Once configured, ask Claude naturally:
Protein & Gene Queries
"Get information about the BRCA1 gene"
"Search UniProt for hemoglobin"
"What protein has UniProt ID P53_HUMAN?"
Clinical Variants
"Is the BRCA1 variant rs80357906 pathogenic?"
"Search ClinVar for TP53 variants"
Protein Interactions
"What proteins interact with TP53?"
"Find functional enrichment for BRCA1, ATM, and CHEK2"
Structures & Pathways
"Get the AlphaFold structure for TP53"
"What pathways is BRCA1 involved in?"
"Search PDB for insulin structures"
Drug Discovery
"What drugs target EGFR?"
"What diseases is BRAF associated with?"
Genetic Diseases
"Search OMIM for cystic fibrosis"
"What diseases are linked to the CFTR gene?"
⚡ Performance Features
- Smart Caching - API responses cached for 1 hour to improve speed
- Async Operations - All API calls are non-blocking
- Error Handling - Graceful handling of API failures
🔧 Development
From Source
# Clone the repository
git clone https://github.com/zaeyasa/gwas-mcp.git
cd gwas-mcp
# Install dependencies
pip install -e .
# Run the server
python -m gwas_mcp.server
Project Structure
gwas-mcp/
├── src/
│ └── gwas_mcp/
│ ├── server.py # Main MCP server
│ ├── tools/
│ │ ├── protein_tools.py # UniProt, NCBI, Ensembl
│ │ ├── clinical_tools.py # ClinVar, STRING
│ │ ├── structure_tools.py # PDB, KEGG, PharmGKB
│ │ └── advanced_tools.py # AlphaFold, Open Targets, OMIM
│ └── resources/
│ └── db_resources.py # Database resources
├── pyproject.toml
├── README.md
└── LICENSE
📊 Supported Databases
| Database | Type | Description |
|---|---|---|
| UniProt | Protein | Protein sequences and annotations |
| Ensembl | Gene/Variant | Genome browser and variant data |
| NCBI Gene | Gene | Gene information database |
| ClinVar | Clinical | Clinical variant interpretations |
| GWAS Catalog | GWAS | Genome-wide association studies |
| GTEx | Expression | Expression QTL data |
| STRING | Interactions | Protein-protein interactions |
| InterPro | Domains | Protein families and domains |
| AlphaFold | Structure | AI-predicted structures |
| PDB | Structure | Experimental 3D structures |
| KEGG | Pathways | Metabolic and signaling pathways |
| Open Targets | Drug Discovery | Drug targets and disease associations |
| PharmGKB | Pharmacogenomics | Drug-gene interactions |
| OMIM | Diseases | Genetic disease database |
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Model Context Protocol - The MCP specification
- Anthropic - Claude AI and MCP development
- All the amazing bioinformatics databases that make this possible
📬 Contact
- GitHub: @zaeyasa
<p align="center">Made with ❤️ for the bioinformatics community</p>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。