Uniprot

🚀 UniProt MCP Server

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

✨ Features

• Retrieve protein information via UniProt accession numbers.
• Batch retrieve information for multiple proteins.
• Cache with a 24-hour expiration time to improve performance.
• Error handling and logging.
• The provided information includes:
  • Protein name
  • Function description
  • Complete sequence
  • Sequence length
  • Organism

🚀 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 content to the 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

In Claude Desktop with the server configured, you can ask the following questions:

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

For batch queries:

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

📚 Documentation - API Reference

Tools

1. get_protein_info

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

     {
       "accession": "P12345",
       "name": "Test Protein",
       "function": "This is a test protein function.",
       "sequence": "MSRSLLLRFLLFLLLLPPLP",
       "length": 20,
       "organism": "Homo sapiens"
     }
     

2. get_proteins_info

   • Batch retrieve information for multiple proteins.
   • Required parameter: accessions (a list of UniProt accession numbers)
   • Example response:

     [
       {
         "accession": "P12345",
         "name": "Test Protein 1",
         "function": "This is the function of test protein 1.",
         "sequence": "MSRSLLLRFLLFLLLLPPLP",
         "length": 20,
         "organism": "Homo sapiens"
       },
       {
         "accession": "QWERTY",
         "name": "Test Protein 2",
         "function": "This is the function of test protein 2.",
         "sequence": "MSRSLLLRFLLFLLLLPPLP",
         "length": 20,
         "organism": "Homo sapiens"
       }
     ]
     

🚧 Development

Install Dependencies

pip install -r requirements.txt

Run the Server

python server.py

Testing

Use the provided test cases for testing:

pytest tests/

🔧 Technical Details

• Build the web interface using Flask.
• Use the requests library to handle API requests.
• Use the json library to parse and generate JSON data.

❗ Error Handling

Common Errors

1. Invalid Accession Number

   • If the provided UniProt accession number does not exist, the server will return a 404 error.

2. Invalid Accession Numbers in Batch Requests

   • The server will ignore invalid accession numbers and return valid protein information.

🤝 Contribution Guidelines

How to Contribute Code

1. Fork the repository.
2. Create a feature branch.
3. Commit your changes.
4. Push to the remote repository.
5. Submit a pull request.

How to Report Issues

• Submit issues to the GitHub repository.

📄 License

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

🙏 Acknowledgments

• UniProt provides the protein data API.
• Anthropic provides the model context protocol specification.
• All contributors help improve this project.