CrewAI Enterprise MCP server

Connects to CrewAI Enterprise workflows, enabling kickoff and monitoring of collaborative agent teams for complex task delegation without leaving your interface.
Back to servers
Provider
CrewAI
Release date
Mar 20, 2025
Language
Python
Stats
33 stars

The CrewAI Enterprise MCP Server implementation provides deployed CrewAI workflows, allowing you to kick off your deployed crew and monitor their status to get results. This server integrates with Claude Desktop to provide a seamless workflow automation experience.

Installation

Prerequisites

Before installing the CrewAI Enterprise MCP Server, you'll need:

  1. Access credentials from app.crewai.com:

    • MCP_CREWAI_ENTERPRISE_SERVER_URL
    • MCP_CREWAI_ENTERPRISE_BEARER_TOKEN
  2. Claude Desktop application installed on your system

Local Installation

To install the server from a cloned repository:

  1. Clone the repository to your local system
  2. Install the required packages:
pip install mcp mcp[cli]

Setting Up with Claude Desktop

Configuration Steps

  1. Open Claude Desktop
  2. Navigate to Settings > Developer Settings
  3. Add a new MCP server with the following configuration:
{
  "mcpServers": {
    "crewai_enterprise_server": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "<filepath of cloned repo>",
        "/crewai_enterprise_server.py"
      ],
      "env": {
        "MCP_CREWAI_ENTERPRISE_SERVER_URL": "<your_server_url>",
        "MCP_CREWAI_ENTERPRISE_BEARER_TOKEN": "<your_bearer_token>"
      }
    }
  }
}

Make sure to replace:

  • <filepath of cloned repo> with the actual path to your cloned repository
  • <your_server_url> with your CrewAI Enterprise server URL
  • <your_bearer_token> with your authentication token

Using the MCP Server

Available Tools

The MCP server provides two main tools:

  • kickoff_crew: Starts your deployed CrewAI workflow
  • get_crew_status: Checks the status and retrieves results of your running crew

Working with Claude Desktop

Once your MCP server is configured in Claude Desktop, you can:

  1. Access the CrewAI tools from the tools menu
  2. Use the kickoff_crew tool to start your deployed workflow
  3. Monitor progress and retrieve results using the get_crew_status tool

The visual interface in Claude Desktop makes it easy to track your workflow's progress and view the final output of your crew's work.

Troubleshooting

If you encounter issues:

  • Verify your environment variables are correctly set
  • Ensure the file path in your configuration points to the correct location
  • Check that you have the proper permissions and authentication tokens

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later