CrewAI Enterprise MCP Server logo

CrewAI Enterprise MCP Server

by crewAIInc

This is a Model Context Protocol (MCP) server implementation that provides deployed CrewAI workflows. It enables kicking off your deployed crew and inspecting the status, giving the results of your crew.

View on GitHub

Last updated: N/A

What is CrewAI Enterprise MCP Server?

The CrewAI Enterprise MCP Server is a server implementation based on the Model Context Protocol (MCP). It allows users to deploy and manage CrewAI workflows, enabling them to initiate crews, monitor their status, and retrieve results.

How to use CrewAI Enterprise MCP Server?

To use the server, you need to set up the required environment variables (MCP_CREWAI_ENTERPRISE_SERVER_URL and MCP_CREWAI_ENTERPRISE_BEARER_TOKEN) obtained from app.crewai.com. For local usage, clone the repository and install mcp and mcp[cli] locally. Then, configure Claude Desktop by adding a new MCP server with the provided JSON configuration, ensuring to replace the placeholders with your actual server URL and bearer token.

Key features of CrewAI Enterprise MCP Server

  • Workflow Deployment

  • Crew Initiation

  • Status Monitoring

  • Result Retrieval

  • Integration with Claude Desktop

Use cases of CrewAI Enterprise MCP Server

  • Automated Task Execution

  • AI-Driven Workflow Management

  • Orchestration of AI Agents

  • Integration with AI Assistants

  • Real-time Workflow Monitoring

FAQ from CrewAI Enterprise MCP Server

What is MCP?

MCP stands for Model Context Protocol. It's a protocol for interacting with AI models and workflows.

Where do I get the MCP_CREWAI_ENTERPRISE_SERVER_URL and MCP_CREWAI_ENTERPRISE_BEARER_TOKEN?

You can retrieve these from app.crewai.com.

Can I run this server locally?

Yes, you can run it locally by cloning the repo and following the instructions in the README.

What tools are provided by this server?

The server provides the kickoff_crew and get_crew_status tools.

Is this server compatible with other AI tools besides Claude Desktop?

The README specifically mentions Claude Desktop integration, but it may be possible to integrate with other tools that support MCP.