CrewAI Enterprise

v1.0.0Coding Agentsstable

A Model Context Protocol server that enables users to kickoff and monitor deployed CrewAI workflows through Claude Desktop.

crewai-enterprise-mcp-servermcpai-integration
Share:
51
Stars
0
Downloads
0
Weekly
0/5

What is CrewAI Enterprise?

CrewAI Enterprise is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that enables users to kickoff and monitor deployed crewai workflows through claude desktop.

A Model Context Protocol server that enables users to kickoff and monitor deployed CrewAI workflows through Claude Desktop.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Model Context Protocol server that enables users to kickof

Use Cases

Deploy and monitor CrewAI workflows through Claude Desktop.
crewAIInc

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 12, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx crewai-enterprise-mcp-server

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 CrewAI Enterprise

CrewAI Enterprise MCP Server is a lightweight MCP server that bridges Claude Desktop (or any MCP client) with deployed CrewAI workflows hosted on the CrewAI Enterprise platform at app.crewai.com. It exposes two tools — kickoff_crew and get_crew_status — allowing you to trigger multi-agent AI workflows and poll their results through a simple natural-language conversation. Teams use it to kick off complex CrewAI pipelines (research, report generation, data processing) and monitor their progress without leaving their AI client.

Prerequisites

  • Python 3.10 or higher
  • uv and the mcp[cli] package installed
  • A CrewAI Enterprise account at app.crewai.com with at least one deployed crew
  • MCP_CREWAI_ENTERPRISE_SERVER_URL: your crew's endpoint URL from app.crewai.com
  • MCP_CREWAI_ENTERPRISE_BEARER_TOKEN: your bearer token from app.crewai.com
1

Clone the repository

Clone the CrewAI Enterprise MCP server repository to your local machine.

git clone https://github.com/crewAIInc/enterprise-mcp-server.git
cd enterprise-mcp-server
2

Install uv and mcp dependencies

Install the uv package manager if you do not have it, then install the required MCP packages.

pip install uv
pip install mcp mcp[cli]
3

Retrieve your CrewAI Enterprise credentials

Log into app.crewai.com, navigate to your deployed crew, and copy the Server URL and Bearer Token. These are the values for the two required environment variables.

4

Configure Claude Desktop

Open Claude Desktop settings, go to Developer Settings, and add a new MCP server entry. Replace the filepath with the absolute path to your cloned repository and fill in your credentials in the env block.

{
  "mcpServers": {
    "crewai_enterprise_server": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "/absolute/path/to/enterprise-mcp-server/crewai_enterprise_server.py"
      ],
      "env": {
        "MCP_CREWAI_ENTERPRISE_SERVER_URL": "https://your-crew-url.crewai.com",
        "MCP_CREWAI_ENTERPRISE_BEARER_TOKEN": "your-bearer-token-here"
      }
    }
  }
}
5

Restart Claude Desktop and verify

Restart Claude Desktop after saving the configuration. The kickoff_crew and get_crew_status tools should appear in the available tools list.

CrewAI Enterprise Examples

Client configuration (Claude Desktop)

Full claude_desktop_config.json entry for the CrewAI Enterprise MCP server. Both environment variables are required and must be retrieved from app.crewai.com.

{
  "mcpServers": {
    "crewai_enterprise_server": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "/Users/yourname/enterprise-mcp-server/crewai_enterprise_server.py"
      ],
      "env": {
        "MCP_CREWAI_ENTERPRISE_SERVER_URL": "https://your-crew-url.crewai.com",
        "MCP_CREWAI_ENTERPRISE_BEARER_TOKEN": "your-bearer-token-here"
      }
    }
  }
}

Prompts to try

These prompts exercise the two available tools: kickoff_crew to start a workflow and get_crew_status to poll for results.

- "Kick off the crew with the topic 'AI trends in healthcare 2025' and wait for the results"
- "Start my research crew and check its status every 30 seconds until it's done"
- "What is the current status of the last crew run?"
- "Trigger the data analysis crew with input {'dataset': 'sales_q4.csv'} and show me the output when complete"

Troubleshooting CrewAI Enterprise

kickoff_crew returns 401 Unauthorized

Your MCP_CREWAI_ENTERPRISE_BEARER_TOKEN is incorrect or expired. Regenerate the token from app.crewai.com and update it in your claude_desktop_config.json. Restart Claude Desktop after making the change.

The server fails to start with 'command not found: uv'

Install uv with 'pip install uv' or 'curl -LsSf https://astral.sh/uv/install.sh | sh'. Make sure the uv binary is on your PATH. You can also use the full absolute path to uv in the 'command' field of your config.

get_crew_status shows the crew is still running after a long time

CrewAI Enterprise workflows can take minutes to hours depending on the number of agents and tasks. If the crew appears stuck, log into app.crewai.com directly to check for errors in the run log. Timeouts and failures are reported in the platform UI.

Frequently Asked Questions about CrewAI Enterprise

What is CrewAI Enterprise?

CrewAI Enterprise is a Model Context Protocol (MCP) server that model context protocol server that enables users to kickoff and monitor deployed crewai workflows through claude desktop. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install CrewAI Enterprise?

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

Which AI clients work with CrewAI Enterprise?

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

Is CrewAI Enterprise free to use?

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

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.

Quick Config Preview

{ "mcpServers": { "crewai-enterprise-mcp-server": { "command": "npx", "args": ["-y", "crewai-enterprise-mcp-server"] } } }

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

Read the full setup guide →

Ready to use CrewAI Enterprise?

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