PRIDE Archive Search MCP server

Enables searching and retrieving proteomics datasets from the PRIDE Archive database with support for keyword filtering, pagination, and custom sorting options
Back to servers
Setup instructions
Provider
Suresh Hewapathirana
Release date
Apr 09, 2025
Language
Python
Stats
2 stars

The PRIDE Archive Search MCP Server provides a Model Context Protocol (MCP)-compliant API that enables AI models to search and interact with proteomics datasets from the PRIDE Archive repository. This server bridges the gap between large language models and scientific proteomics data through structured function calls.

Installation

To install the MCP PRIDE Archive Search Server:

git clone https://github.com/PRIDE-Archive/mcp_pride_archive_search.git
cd mcp_pride_archive_search
poetry install  # or pip install -r requirements.txt

Server Configuration

Start the MCP server by specifying your preferred connection type:

python -m mcp_pride_archive_search --connection_type http --port 9999

Command-line Arguments

Argument Description Default
--connection_type Type of connection: http or stdio http
--port Port to run the server (HTTP mode) 9999

Available Tools

search_archive_tool

This tool fetches proteomics datasets from the PRIDE Archive database.

You should use this tool when:

  • Searching for proteomics research data
  • Running mass spectrometry dataset queries
  • Exploring biomedical datasets (e.g., cancer-related)
  • Finding popular or specific proteomics projects

Integration with Language Models

The server is compatible with any LLM supporting the Model Context Protocol, including:

  • Anthropic Claude
  • Google Gemini
  • Open-source MCP clients
  • Custom RAG pipelines

The server architecture connects these models to the PRIDE Archive REST API (https://www.ebi.ac.uk/pride/ws/archive/v3/search/projects), enabling AI systems to query and analyze proteomics data programmatically.

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 "mcp_pride_archive_search" '{"command":"python","args":["-m","mcp_pride_archive_search","--connection_type","http","--port","9999"]}'

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": {
        "mcp_pride_archive_search": {
            "command": "python",
            "args": [
                "-m",
                "mcp_pride_archive_search",
                "--connection_type",
                "http",
                "--port",
                "9999"
            ]
        }
    }
}

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": {
        "mcp_pride_archive_search": {
            "command": "python",
            "args": [
                "-m",
                "mcp_pride_archive_search",
                "--connection_type",
                "http",
                "--port",
                "9999"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later