UniProt MCP server for AI agents

This UniProt MCP server provides comprehensive access to the UniProt protein database through the Model Context Protocol, offering 26 specialized bioinformatics tools for protein research, genomics analysis, and structural biology investigations.

Installation

Prerequisites

Node.js (v16 or higher)
npm or yarn

Setup

Clone the repository:

git clone <repository-url>
cd uniprot-server

Install dependencies:

npm install

Build the project:

npm run build

Docker Installation

Building the Docker Image

docker build -t uniprot-mcp-server .

Running with Docker

docker run -i uniprot-mcp-server

For MCP client integration:

{
  "mcpServers": {
    "uniprot": {
      "command": "docker",
      "args": ["run", "-i", "uniprot-mcp-server"],
      "env": {}
    }
  }
}

Docker Compose (Optional)

Create a docker-compose.yml file:

version: "3.8"
services:
  uniprot-mcp:
    build: .
    image: uniprot-mcp-server
    stdin_open: true
    tty: true

Run with:

docker-compose up

Usage

As an MCP Server

Run the server via stdio:

npm start

Adding to MCP Client Configuration

Add the server to your MCP client configuration:

{
  "mcpServers": {
    "uniprot": {
      "command": "node",
      "args": ["/path/to/uniprot-server/build/index.js"],
      "env": {}
    }
  }
}

Available Tools

Core Protein Analysis

search_proteins

Search the UniProt database for proteins.

Parameters:

query (required): Search query (protein name, keyword)
organism (optional): Organism name or taxonomy ID
size (optional): Number of results (1-500, default: 25)
format (optional): Output format (json, tsv, fasta, xml)

Example:

{
  "query": "insulin",
  "organism": "human",
  "size": 5
}

get_protein_info

Get detailed information for a specific protein.

Parameters:

accession (required): UniProt accession number
format (optional): Output format

Example:

{
  "accession": "P01308",
  "format": "json"
}

search_by_gene

Search for proteins by gene name or symbol.

Parameters:

gene (required): Gene name or symbol
organism (optional): Organism name or taxonomy ID
size (optional): Number of results (1-500, default: 25)

Example:

{
  "gene": "BRCA1",
  "organism": "human"
}

get_protein_sequence

Get the amino acid sequence for a protein.

Parameters:

accession (required): UniProt accession number
format (optional): Output format (fasta, json)

Example:

{
  "accession": "P01308",
  "format": "fasta"
}

get_protein_features

Get functional features and domains for a protein.

Parameters:

accession (required): UniProt accession number

Example:

{
  "accession": "P01308"
}

Resource Templates

Direct access to UniProt data through URI templates:

Protein Information

URI: uniprot://protein/{accession}
Example: uniprot://protein/P01308

Protein Sequence

URI: uniprot://sequence/{accession}
Example: uniprot://sequence/P01308

Search Results

URI: uniprot://search/{query}
Example: uniprot://search/insulin

Example Usage

Basic Protein Search

{
  "tool": "search_proteins",
  "arguments": {
    "query": "insulin",
    "organism": "human",
    "size": 10
  }
}

Get Detailed Protein Information

{
  "tool": "get_protein_info",
  "arguments": {
    "accession": "P01308"
  }
}

Gene-based Search

{
  "tool": "search_by_gene",
  "arguments": {
    "gene": "BRCA1",
    "organism": "human"
  }
}

Retrieve Protein Sequence

{
  "tool": "get_protein_sequence",
  "arguments": {
    "accession": "P01308",
    "format": "fasta"
  }
}

Analyze Protein Features

{
  "tool": "get_protein_features",
  "arguments": {
    "accession": "P01308"
  }
}

API Integration

This server integrates with the UniProt REST API. For more information:

UniProt Website: https://www.uniprot.org/
API Documentation: https://www.uniprot.org/help/api
REST API Guide: https://www.uniprot.org/help/api_queries

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "uniprot" '{"command":"node","args":["/path/to/uniprot-server/build/index.js"],"env":[]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "uniprot": {
            "command": "node",
            "args": [
                "/path/to/uniprot-server/build/index.js"
            ],
            "env": []
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

{
    "mcpServers": {
        "uniprot": {
            "command": "node",
            "args": [
                "/path/to/uniprot-server/build/index.js"
            ],
            "env": []
        }
    }
}

3. Restart Claude Desktop for the changes to take effect