🧬 MCP PRIDE Archive Search Server

By PRIDE-Archive GitHub

Model Context Protocol (MCP) PRIDE API Server implementation.

mcp pride

Overview

What is MCP PRIDE Archive Search?

MCP PRIDE Archive Search is an API server that implements the Model Context Protocol (MCP) to facilitate programmatic access to the PRIDE Archive, a repository for proteomics data.

How to use MCP PRIDE Archive Search?

To use the server, clone the repository, install the dependencies, and start the server with your preferred connection type (http or stdio).

Key features of MCP PRIDE Archive Search?

MCP Server powered by FastMCP
Search tool for querying datasets by various parameters
AI-friendly tools for biomedical research
Supports both http and stdio connection modes
Easily extendable with additional tools

Use cases of MCP PRIDE Archive Search?

Searching for proteomics research data.
Querying mass spectrometry datasets.
Exploring biomedical datasets related to cancer.
Finding specific or popular proteomics projects.

FAQ from MCP PRIDE Archive Search?

What is the purpose of this API server?

It allows AI models to interact with proteomics datasets programmatically.

How do I install the server?

Clone the repository and install dependencies using poetry or pip.

Can I use this server with any LLM?

Yes, it works with any LLM that supports the Model Context Protocol.

Content

🧬 MCP PRIDE Archive Search Server

This project implements a Model Context Protocol (MCP)-compliant API server that exposes tools to search the PRIDE Archive, a major repository for proteomics data. It allows AI models (such as Claude or other MCP-compatible LLMs) to interact with proteomics datasets programmatically using structured function calling.

🚀 Features

✅ MCP Server powered by FastMCP
🔍 PRIDE Archive Search Tool to query datasets by keyword, submission date, popularity, etc.
🤖 AI-friendly tools for biomedical and proteomics-related research
⚡ Supports both http (SSE) and stdio connection modes
🛠️ Easily extendable with additional tools

📦 Installation

Clone the repo and install dependencies:

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

👨‍💻 Usage

Start the MCP server with your preferred connection type (http or stdio):

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 (for HTTP mode)	9999

🔧 Tool APIs

search_archive_tool(...)

Fetches proteomics datasets from the PRIDE Archive database.

Use this when:

Searching for proteomics research data
Mass spectrometry dataset queries
Biomedical dataset exploration (e.g., cancer-related)
Finding popular or specific proteomics projects

🤝 Integration with LLMs

This server works with any LLM that supports Model Context Protocol, including:

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

🧠 Architecture Overview

+---------------------+       Tool Calls        +-----------------------------+
|  Claude / Gemini AI |  <--------------------> | MCP PRIDE API Server        |
+---------------------+                         | - search_archive_tool()     |
                                                | - server_status()           |
                                                +-----------------------------+
                                                           |
                                                           v
                                              +---------------------------+
                                              | PRIDE Archive REST API    |
                                              | (https://www.ebi.ac.uk    |
                                              |   /pride/ws/archive/      |
                                              |  v3/search/projects)      |
                                              +---------------------------+