Agent MCP
Agent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP). The system is designed for developers building AI applications that benefit from multiple special
What is Agent MCP?
Agent MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to agent-mcp is a framework for creating multi-agent systems that enables coordinated, efficient ai collaboration through the model context protocol (mcp). the system is designed for developers building ...
Agent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP). The system is designed for developers building AI applications that benefit from multiple special
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Agent-MCP is a framework for creating multi-agent systems th
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx agent-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Agent MCP
Agent-MCP is an open-source framework for building multi-agent AI systems where specialized agents collaborate on complex tasks through the Model Context Protocol. A central MCP server coordinates agent creation, task assignment, inter-agent messaging, and a shared RAG knowledge graph so that multiple AI agents — each focused on a specific role such as backend, frontend, or DevOps — can work together on large software projects without losing context or duplicating effort.
Prerequisites
- Python 3.10 or higher and the uv package manager
- Node.js 18 or higher (22.16.0 recommended) and npm 9 or higher
- An OpenAI API key (required for embeddings and the RAG knowledge graph)
- Minimum 4 GB RAM for running multiple concurrent agents
- An MCP client such as Claude Desktop or Claude Code
Clone the repository
Clone the Agent-MCP repository to your local machine and navigate into the project directory.
git clone https://github.com/rinadelph/Agent-MCP.git
cd Agent-MCPSet up the Python environment and install dependencies
Create a virtual environment with uv, copy the example environment file, and add your OpenAI API key. The OPENAI_API_KEY is required for the RAG knowledge graph that stores project context.
uv venv
cp .env.example .env
# Edit .env and set OPENAI_API_KEY=sk-xxxxxxxxxxxx
uv syncStart the Agent-MCP server
Launch the MCP coordination server. It will listen on port 8080 and serve as the hub all agents connect to. Pass --project-dir to set the working directory for agent tasks.
uv run -m agent_mcp.cli --port 8080 --project-dir /path/to/your/projectLaunch the monitoring dashboard (optional)
The web dashboard shows all active agents, their tasks, and message history in real time. Run it in a separate terminal.
cd agent_mcp/dashboard && npm install && npm run dev
# Visit http://localhost:3847Configure your MCP client to connect to Agent-MCP
Add Agent-MCP as an MCP server in your Claude Desktop config. The server must already be running before Claude Desktop starts.
{
"mcpServers": {
"agent-mcp": {
"command": "uv",
"args": ["run", "-m", "agent_mcp.cli", "--port", "8080", "--project-dir", "/path/to/project"],
"env": {
"OPENAI_API_KEY": "sk-xxxxxxxxxxxxxxxxxxxx"
}
}
}
}Create your first agents and assign tasks
Once connected via Claude, use the MCP tools to create specialized agents and assign tasks. Agents can communicate with each other and share a persistent knowledge graph.
Agent MCP Examples
Client configuration
Claude Desktop configuration for Agent-MCP, launching the coordination server with a project directory and OpenAI API key.
{
"mcpServers": {
"agent-mcp": {
"command": "uv",
"args": [
"run",
"-m",
"agent_mcp.cli",
"--port",
"8080",
"--project-dir",
"/Users/you/projects/myapp"
],
"env": {
"OPENAI_API_KEY": "sk-xxxxxxxxxxxxxxxxxxxx",
"AGENT_MCP_MAX_AGENTS": "5"
}
}
}
}Prompts to try
Example prompts to send to Claude once Agent-MCP is connected and the server is running.
- "Create a backend agent specializing in FastAPI and assign it the task of implementing user authentication endpoints"
- "Create a frontend agent for React components and a backend agent for the REST API, then assign them the checkout flow feature"
- "List all active agents and their current task status"
- "Ask the project RAG what architectural decisions have been made so far"
- "Broadcast a message to all agents that the database schema has changed"Troubleshooting Agent MCP
Server fails to start with 'OPENAI_API_KEY not set' error
The RAG knowledge graph requires an OpenAI API key for embeddings. Confirm OPENAI_API_KEY is set in your .env file or passed as an environment variable. Run 'export OPENAI_API_KEY=sk-xxx' and retry.
Claude Desktop cannot connect to the Agent-MCP server
The Agent-MCP server must be running before Claude Desktop starts. Start the server manually first with 'uv run -m agent_mcp.cli --port 8080', confirm it prints 'Server started', then restart Claude Desktop.
Agents are created but tasks never complete
Check AGENT_MCP_MAX_AGENTS — the default limit is 10 concurrent agents. Monitor the dashboard at http://localhost:3847 to see task queues and agent logs. Ensure the --project-dir path exists and is writable.
Frequently Asked Questions about Agent MCP
What is Agent MCP?
Agent MCP is a Model Context Protocol (MCP) server that agent-mcp is a framework for creating multi-agent systems that enables coordinated, efficient ai collaboration through the model context protocol (mcp). the system is designed for developers building ai applications that benefit from multiple special It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Agent MCP?
Follow the installation instructions on the Agent MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Agent MCP?
Agent MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Agent MCP free to use?
Yes, Agent MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Agent MCP Alternatives — Similar Coding Agents Servers
Looking for alternatives to Agent MCP? 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 Agent MCP 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 Agent MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.