Evo AI
Evo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI models and services.
What is Evo AI?
Evo AI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to evo ai is an open-source platform for creating and managing ai agents, enabling integration with different ai models and services.
Evo AI is an open-source platform for creating and managing AI agents, enabling integration with different AI models and services.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Evo AI is an open-source platform for creating and managing
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx evo-aiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Evo AI
Evo AI is an open-source platform for creating, deploying, and orchestrating AI agents that support multiple execution frameworks including Google ADK, CrewAI, and LangGraph. It provides a backend API and a web frontend for designing agent pipelines with seven agent types — LLM, sequential, parallel, loop, workflow, task, and agent-to-agent — along with MCP server integration, JWT authentication, and observability via LangFuse. Teams use it as a self-hosted alternative to managed agent platforms when they need full control over agent logic, model choice, and data.
Prerequisites
- Python 3.10 or higher (for the backend)
- Node.js 18 or higher with pnpm (for the frontend)
- PostgreSQL database running and accessible
- Redis server running (for task queuing and caching)
- Docker and Docker Compose (optional, for containerized deployment)
Clone the repository
Clone the Evo AI repository from the EvolutionAPI GitHub organization.
git clone https://github.com/EvolutionAPI/evo-ai.git
cd evo-aiConfigure environment variables
Copy the example .env file and edit it with your database connection, Redis details, JWT secret, and AI provider settings.
cp .env.example .env
# Edit .env and set:
# POSTGRES_CONNECTION_STRING=postgresql://user:pass@localhost/evoai
# REDIS_HOST=localhost
# REDIS_PORT=6379
# JWT_SECRET_KEY=your-strong-secret
# AI_ENGINE=crewai # or 'adk'
# ENCRYPTION_KEY=your-encryption-keySet up the backend
Create a virtual environment, install Python dependencies, run database migrations, and seed initial data.
make venv
make install-dev
make alembic-upgrade
make seed-allSet up and run the frontend
Install frontend dependencies and configure the API URL environment variable, then start the development server.
cd frontend
pnpm install
# Create frontend/.env and set:
# NEXT_PUBLIC_API_URL=http://localhost:8000
pnpm devStart the backend server
Run the backend API server. The Swagger API docs will be available at http://localhost:8000/docs.
make run(Optional) Deploy with Docker
Build and start the complete stack using Docker Compose for a production-ready deployment.
make docker-build
make docker-upEvo AI Examples
Client configuration
Key environment variables for the Evo AI backend .env file.
{
"mcpServers": {
"evo-ai": {
"command": "npx",
"args": ["evo-ai"],
"env": {
"NEXT_PUBLIC_API_URL": "http://localhost:8000"
}
}
}
}Prompts to try
Use these prompts when interacting with agents built on the Evo AI platform.
- "Create a sequential agent pipeline that first researches a topic, then writes a summary, then formats it as HTML"
- "Set up a parallel agent that simultaneously queries three different APIs and merges the results"
- "Build a loop agent that keeps refining a draft until a quality score exceeds 0.9"
- "Register a new MCP server tool in the Evo AI platform and assign it to an agent"
- "Show me the execution trace for the last agent run using LangFuse"Troubleshooting Evo AI
Database migration fails with connection refused error
Ensure PostgreSQL is running and the POSTGRES_CONNECTION_STRING in .env is correct. Test with: psql $POSTGRES_CONNECTION_STRING -c 'SELECT 1'. Also check that the database user has CREATE TABLE permissions.
JWT authentication errors when calling the API
Ensure JWT_SECRET_KEY is set and consistent between restarts. If you changed the key after seeding, existing tokens will be invalid — regenerate them by logging in again through the frontend or API.
Agent tasks are queued but never executed
Verify Redis is running on the configured REDIS_HOST and REDIS_PORT. Run 'redis-cli ping' and confirm it returns PONG. The Evo AI task queue depends on Redis being accessible from the backend process.
Frequently Asked Questions about Evo AI
What is Evo AI?
Evo AI is a Model Context Protocol (MCP) server that evo ai is an open-source platform for creating and managing ai agents, enabling integration with different ai models and services. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Evo AI?
Follow the installation instructions on the Evo AI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Evo AI?
Evo AI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Evo AI free to use?
Yes, Evo AI is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Evo AI Alternatives — Similar Coding Agents Servers
Looking for alternatives to Evo AI? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Evo AI in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Evo AI?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.