Uniprot MCP Server

🚀 UniProt MCP Server

A Model Context Protocol (MCP) server that provides protein information from UniProt. This server allows AI assistants to directly retrieve protein function and sequence information from UniProt.

✨ Features

• Retrieve protein information via UniProt accession numbers.
• Perform batch retrieval of information for multiple proteins.
• Utilize a cache with a 24-hour expiration time to enhance performance.
• Implement error handling and logging.
• Provide the following information:
  • Protein name
  • Function description
  • Complete sequence
  • Sequence length
  • Biological species

🚀 Quick Start

1. Ensure that Python 3.10 or a higher version is installed.
2. Clone this repository:

   git clone https://github.com/TakumiY235/uniprot-mcp-server.git
   cd uniprot-mcp-server
   

3. Install the dependencies:

   # Use uv (recommended)
   uv pip install -r requirements.txt
   
   # Or use pip
   pip install -r requirements.txt
   

📚 Documentation

Add the following to your Claude Desktop configuration file:

• Windows: %APPDATA%\Claude\claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "uniprot": {
      "command": "uv",
      "args": ["--directory", "path/to/uniprot-mcp-server", "run", "uniprot-mcp-server"]
    }
  }
}

💻 Usage Examples

After configuring the server in Claude Desktop, you can ask the following questions:

Basic Usage

Can you get the protein information for UniProt accession number P98160?

Advanced Usage

Can you get and compare the protein information for two UniProt accession numbers, P04637 and P02747?

📚 Documentation

Tools

1. get_protein_info

   • Retrieve information for a single protein.
   • Required parameter: accession (UniProt accession number).
   • Example response:

     {
       "accession": "P12345",
       "name": "Protein name",
       "function": "Protein function description",
       "sequence": "MKTMDVLLMVLTALAVLYQRL...",
       "length": 1024,
       "species": "Homo sapiens"
     }
     

2. get_batch_proteins

   • Retrieve information for multiple proteins in batch.
   • Required parameter: accessions (a list containing multiple accession numbers).
   • Optional parameter: include_sequence (whether to include the sequence, default is true).

🔧 Technical Details

• Use httpx for HTTP requests.
• Implement a cache based on OrderedDict.
• Support multi-threaded processing of concurrent requests.
• Incorporate a built-in error handling mechanism.

🚫 Error Handling

Possible Errors

1. Invalid accession number

   • Return 400 Bad Request.
   • Example response:

     {
       "error": "Invalid accession number"
     }
     

2. Network error

   • Return 503 Service Unavailable.
   • Example response:

     {
       "error": "Network error occurred while fetching data"
     }
     

🤝 Contribution Guidelines

How to Contribute

1. Fork the repository: git clone https://github.com/TakumiY235/uniprot-mcp-server.git
2. Create a feature branch: git checkout -b feature/your-feature-name
3. Commit your changes: git commit -m "Your commit message"
4. Push to the remote repository: git push origin feature/your-feature-name
5. Submit a pull request.

Code Style

• Follow the PEP8 coding standard.
• Use meaningful variable names.
• Add detailed comments.
• Ensure code readability.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• UniProt for providing the protein data API.
• Anthropic for providing the model context protocol specification.
• All contributors who helped improve this project.