PRIDE Archive Search

A PRIDE Archive search service project based on the MCP protocol, providing proteomics data query functions for AI models.

Research and data Search tools #Proteomics #MCP service #Data search #AI tool .Python

rating : 2.5 points

downloads : 6.2K

update time : 2025-04-28

Open Site

What is the MCP PRIDE Archive Search Server?

The MCP PRIDE Archive Search Server is an API server that supports the Model Context Protocol (MCP). It allows users to programmatically search the PRIDE Archive, an important proteomics data repository. You can use this tool to find research data related to mass spectrometry and explore datasets on specific topics or time periods.

How to use the MCP PRIDE Archive Search Server?

After starting the server, you can interact with it via HTTP or standard input/output mode. Then use the provided API interfaces to perform query operations.

Applicable scenarios

Suitable for researchers who need to access proteomics data, such as those looking for datasets related to specific diseases or analyzing popular trends.

Main features

Supports Model Context Protocol (MCP)

Follows the MCP standard, enabling AI models to easily call this service.

PRIDE Archive search tool

Allows querying proteomics datasets based on factors such as keywords, submission dates, and popularity.

Multiple connection modes

Supports both HTTP (SSE) and standard input/output modes.

Easy to expand

More features can be added to meet different needs.

Advantages

MCP protocol that meets industry standards

Powerful search capabilities covering a wide range of datasets

High flexibility, supporting multiple usage scenarios

Limitations

Requires a certain technical background to set up the environment

Custom scripts may be required for non - conventional queries

How to use

Install dependencies

First, make sure that Git and Python environments are installed on your computer.

Start the server

Run the following command to start the MCP PRIDE Archive Search Server.

Usage examples

Example 1: Search for cancer - related data

Demonstrate how to search for proteomics data related to cancer.

Example 2: Get the server status

Show how to verify whether the server is running normally.

Frequently Asked Questions

How to confirm whether my Python version is compatible?

What should I do if I encounter a connection failure?

Related resources

Official documentation

Detailed user manuals and technical guides.

GitHub repository

Source code and contribution guidelines.

PRIDE Archive homepage

Understand the core functions and services of the PRIDE Archive.

🚀 MCP PRIDE Database Search Server

This project implements an API server compliant with the Model Context Protocol (MCP) standard, offering tools to search the PRIDE Database, a crucial proteomics data repository. It enables AI models (such as Claude or other MCP-compatible large language models) to programmatically interact with proteomics datasets through structured function calls.

🚀 Quick Start

This server allows AI models to interact with proteomics datasets in the PRIDE Database. It provides a structured way for models to query data, facilitating research in biomedicine and proteomics.

✨ Features

✅ MCP server powered by FastMCP
🔍 PRIDE database search tool, capable of querying datasets by keywords, submission date, popularity, etc.
🤖 AI-friendly tool suitable for biomedical and proteomics research
⚡ Supports http (SSE) and stdio connection modes
🛠️ Easy to extend to add more tools

📦 Installation

Clone the repository and install the 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 Examples

Basic Usage

Start the MCP server with your chosen connection type:

python -m mcp_pride_ARCHIVE_SEARCH --connection_type http --port 9999

Command-line Argument Details

Property	Details
--connection_type	Connection type: http or stdio. Default is `http`.
--port	The port on which the server runs (for HTTP mode). Default is `9999`.

🔧 Technical Details

search_archive_tool(...)

Retrieve proteomics datasets from the PRIDE database.

Use cases:

Search for proteomics research data
Query for mass spectrometry data analysis
Explore biomedical data (e.g., cancer-related research)
Find specific or popular proteomics projects

🤝 Integration with LLMs

This server can be used with any LLM that supports the Model Context Protocol, including:

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

🧠 Architecture Overview

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