MCP Directory

How to add Agent-MCP to Claude Desktop

Multi-agent collaboration protocol: orchestrate specialized AI agents over MCP with a shared knowledge graph. Paste the config into ~/Library/Application Support/Claude/claude_desktop_config.json and restart Claude Desktop.

Last updated June 14, 2026 · 1.2k★ · stdio · apikey

Claude Desktop config for Agent-MCP

uv venv && uv install
{
  "mcpServers": {
    "agent-mcp": {
      "command": "uv",
      "args": [
        "run",
        "-m",
        "agent_mcp.cli",
        "--port",
        "8080"
      ],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key"
      }
    }
  }
}

Setup steps

  1. 1Open Claude Desktop → Settings → Developer → Edit Config (this opens ~/Library/Application Support/Claude/claude_desktop_config.json).
  2. 2Paste the Agent-MCP config below under the top-level "mcpServers" key.
  3. 3Fill in any placeholder secrets (API keys, paths) in the snippet.
  4. 4Save the file, then fully quit and reopen Claude Desktop.
  5. 5Open a chat and confirm Agent-MCP's tools appear under the 🔌 tools menu.

Before you start

  • Python 3.10+ (with uv or pip)
  • Node.js 18.0.0+ (recommended 22.16.0) and npm 9.0.0+ for the dashboard / Node implementation
  • OpenAI API key (for embeddings and RAG)
  • 4GB RAM minimum
  • An AI coding assistant such as Claude Code or Cursor

What Agent-MCP can do in Claude Desktop

create_agent

Spawn specialized agents (backend, frontend, testing, etc.).

list_agents

View all active agents and their status.

terminate_agent

Safely shut down agents.

assign_task

Delegate work to specific agents.

view_tasks

Monitor task progress and dependencies.

update_task_status

Track task completion and blockers.

ask_project_rag

Query the persistent knowledge graph.

update_project_context

Add architectural decisions and patterns to project context.

Security

Requires an OpenAI API key (set via OPENAI_API_KEY) for embeddings and RAG. The server uses admin/worker tokens; the admin token is printed in the server startup logs. Server can optionally bind to 0.0.0.0 and accept an --auth-token, so restrict network exposure accordingly.

Agent-MCP + Claude Desktop FAQ

Where is the Claude Desktop config file?

Claude Desktop reads MCP servers from ~/Library/Application Support/Claude/claude_desktop_config.json. Paste the Agent-MCP config there under the "mcpServers" key and restart the client.

Is Agent-MCP safe to use with Claude Desktop?

Requires an OpenAI API key (set via OPENAI_API_KEY) for embeddings and RAG. The server uses admin/worker tokens; the admin token is printed in the server startup logs. Server can optionally bind to 0.0.0.0 and accept an --auth-token, so restrict network exposure accordingly.

Which implementation should I use?

The README recommends the Python implementation, started with `uv run -m agent_mcp.cli --port 8080`. A Node.js/TypeScript implementation is also available and can be installed globally via the agent-mcp-node npm package.

How do I connect it to Claude Desktop?

Add an entry to claude_desktop_config.json under mcpServers with command `uv` and args `["run", "-m", "agent_mcp.cli", "--port", "8080"]`, set OPENAI_API_KEY in env, then restart Claude Desktop. Claude should show the agent-mcp server in the conversation.

Why does it use short-lived agents?

Each agent is purpose-built for a single task with minimal, focused context. This keeps behavior deterministic, reduces hallucination and the attack surface, and avoids the context bloat of long-running agents. The framework enforces a maximum of 10 active agents and automatic cleanup of idle/finished agents.

View repo Full Agent-MCP page