UniProt MCP Server

UniProt MCP Server is an MCP server that provides AI assistants direct access to protein data from the UniProt database. Built using the Model Context Protocol Python SDK, it connects language models directly to UniProt REST APIs to retrieve functional annotations, sequence information, and taxonomic details. Bioinformaticians, computational biologists, and life science researchers use this server to automate biological data retrieval and examine protein characteristics without manually searching web databases. The server allows assistants to fetch comprehensive records using specific UniProt accession numbers, supporting both single-item queries and batch operations. Returned information includes protein names, detailed functional descriptions, full amino acid sequences, sequence lengths, and host organism classifications. To optimize performance and reduce external network calls, the server incorporates an in-memory cache with a 24-hour time-to-live mechanism. It also manages network retries, rates limits, and invalid accession errors automatically.

Category: Other & General Purpose

Tags: bioinformatics, biology, genomics, proteins, uniprot

Visit UniProt MCP Server

How to install and configure UniProt MCP Server

1. Ensure Python 3.10 or higher is installed on your system. 2. Clone the repository: bash git clone https://github.com/TakumiY235/uniprot-mcp-server.git cd uniprot-mcp-server 3. Install dependencies using uv or pip: bash uv pip install -r requirements.txt # Or using pip pip install -r requirements.txt 4. Add the server configuration to your Claude Desktop configuration file (claude_desktop_config.json): json { "mcpServers": { "uniprot": { "command": "uv", "args": ["--directory", "path/to/uniprot-mcp-server", "run", "uniprot-mcp-server"] } } } 5. Replace path/to/uniprot-mcp-server with your actual local repository path and restart Claude Desktop.

What you can do with UniProt MCP Server

• Fetching functional descriptions and full amino acid sequences for specific proteins using their unique UniProt accession numbers. - Performing batch retrieval across multiple protein accessions to quickly compare sequence lengths and biological roles within Claude. - Extracting organism details and scientific protein names for automated literature reviews and bioinformatics research documentation. - Feeding accurate protein sequence data directly to downstream analysis workflows without manual file exports or copy-pasting.

Key facts

• https://github.com/TakumiY235/uniprot-mcp-server
• Other & General Purpose, Web Search & Research
• bioinformatics, biology, genomics, proteins, uniprot

Part of MCP Servers

What can UniProt MCP Server do?

UniProt MCP Server enables AI assistants to query the UniProt database. It can fetch full protein sequences, lengths, functional descriptions, common and scientific names, and organism classifications. It provides tools for both individual protein lookup and batch retrieval across multiple accession numbers.

How do I install UniProt MCP Server?

You can install it by cloning the GitHub repository and installing the requirements via pip or uv in a Python 3.10+ environment. Then, add the server command to your Claude Desktop JSON configuration file with the local directory path.

Which MCP clients work with UniProt MCP Server?

The server works with any Model Context Protocol compliant client, such as Claude Desktop. It runs locally via standard input/output using Python and the MCP SDK.

Does UniProt MCP Server cache query results?

Yes, the server includes built-in caching using an OrderedDict structure with a 24-hour time-to-live. Repeated requests for the same UniProt accession number are served from cache to improve speed and reduce API traffic.

Is UniProt MCP Server open source?

Yes, UniProt MCP Server is open source and licensed under the MIT License on GitHub.