MCPgee
MCPgee
MCPgeeMCPgee

GEPA

v1.0.0•Data Science & ML•stable

MCP server integrating GEPA (Genetic-Evolutionary Prompt Architecture) for automatic prompt optimization with Claude Desktop

aiclaude-desktopevolutionary-algorithmsgemini-aigenetic-algorithms
Share:
48
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is GEPA?

GEPA is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server integrating gepa (genetic-evolutionary prompt architecture) for automatic prompt optimization with claude desktop

MCP server integrating GEPA (Genetic-Evolutionary Prompt Architecture) for automatic prompt optimization with Claude Desktop

This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server integrating GEPA (Genetic-Evolutionary Prompt Arc

Use Cases

Automatic prompt optimization
Genetic algorithm-based improvement
developzir

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedApr 3, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx gepa

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use GEPA

The GEPA MCP Server integrates Genetic-Evolutionary Prompt Architecture — an automated prompt optimization system — into Claude Desktop, enabling AI-driven refinement of prompts using genetic algorithms powered by the Google Gemini API. Rather than manually iterating on prompts, GEPA evolves them over multiple generations against training examples, making it useful for teams that need to optimize prompt templates for classification, extraction, or generation tasks. The server exposes three optimization strategies: full evolutionary optimization with training data, quick single-cycle improvement, and context-aware conversational optimization.

Prerequisites

  • Python 3.10+ installed on your system
  • A Google Gemini API key (free tier available at ai.google.dev)
  • Git for cloning the repository
  • An MCP client such as Claude Desktop
1

Clone the repository

Download the GEPA MCP server source code from GitHub.

git clone https://github.com/developzir/gepa-mcp.git
cd gepa-mcp
2

Run the install script

The included install.sh script sets up the Python virtual environment and installs all dependencies.

./install.sh
3

Obtain a Gemini API key

Go to ai.google.dev, sign in with your Google account, and create a Gemini API key. Copy it for the next step. The default model used is gemini-1.5-flash.

4

Configure Claude Desktop

Add the GEPA server to your claude_desktop_config.json with your Gemini API key and optional parameters for model, temperature, and optimization budget.

{
  "mcpServers": {
    "gepa": {
      "command": "python",
      "args": ["/path/to/gepa-mcp/server.py"],
      "env": {
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY",
        "GEMINI_MODEL": "gemini-1.5-flash",
        "TEMPERATURE": "0.7",
        "DEFAULT_BUDGET": "10"
      }
    }
  }
}
5

Restart Claude Desktop and test

Fully quit and relaunch Claude Desktop. Ask Claude to optimize a prompt using the quick_prompt_improve tool to verify connectivity.

GEPA Examples

Client configuration

Claude Desktop configuration for the GEPA server with Gemini API access.

{
  "mcpServers": {
    "gepa": {
      "command": "python",
      "args": ["/Users/you/gepa-mcp/server.py"],
      "env": {
        "GEMINI_API_KEY": "AIzaSyYOUR_GEMINI_KEY",
        "GEMINI_MODEL": "gemini-1.5-flash",
        "TEMPERATURE": "0.7",
        "DEFAULT_BUDGET": "10"
      }
    }
  }
}

Prompts to try

Example prompts that exercise the three GEPA optimization tools.

- "Use quick_prompt_improve to enhance this prompt: 'Summarize the following article'"
- "Optimize this classification prompt using training examples: seed='Classify the sentiment of this review', examples=[{input:'Great product!', keywords:['positive']},{input:'Terrible quality', keywords:['negative']}]"
- "Use conversational_optimize to refine my current prompt based on the last few exchanges"

Troubleshooting GEPA

Server fails to start with 'GEMINI_API_KEY not set' error

Ensure GEMINI_API_KEY is included in the env block of your claude_desktop_config.json and that you have fully restarted Claude Desktop after editing the config file.

Optimization runs slowly or times out

Reduce the DEFAULT_BUDGET environment variable (try 5 instead of 10) or lower the budget parameter when calling optimize_prompt. The budget controls how many evolutionary generations are run, directly impacting runtime.

install.sh fails with permission errors

Run chmod +x install.sh before executing it. If Python dependencies fail to install, ensure pip is available and try running pip install -r requirements.txt manually inside the cloned directory.

Frequently Asked Questions about GEPA

What is GEPA?

GEPA is a Model Context Protocol (MCP) server that mcp server integrating gepa (genetic-evolutionary prompt architecture) for automatic prompt optimization with claude desktop It connects AI assistants to external tools and data sources through a standardized interface.

How do I install GEPA?

Follow the installation instructions on the GEPA GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with GEPA?

GEPA works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is GEPA free to use?

Yes, GEPA is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

GEPA Alternatives — Similar Data Science & ML Servers

Looking for alternatives to GEPA? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Data Science & MLBrowse All Servers

Quick Config Preview

{ "mcpServers": { "gepa": { "command": "npx", "args": ["-y", "gepa"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use GEPA?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides