CrewAI Workflow MCP server

The MCP Crew AI Server is a lightweight Python-based solution that helps you run, manage and create CrewAI workflows. It uses the Model Context Protocol (MCP) to communicate with Large Language Models and tools like Claude Desktop or Cursor IDE, making it easy to orchestrate multi-agent workflows without extensive coding.

Installation Options

Install from PyPI (Recommended)

pip install mcp-crew-ai

Install from GitHub

pip install git+https://github.com/adam-paterson/mcp-crew-ai.git

Clone and Install Locally

git clone https://github.com/adam-paterson/mcp-crew-ai.git
cd mcp-crew-ai
pip install -e .

System Requirements

• Python 3.11 or newer
• MCP SDK
• CrewAI
• PyYAML

Configuration Files

The server uses two YAML files to configure your workflow:

Agents Configuration

Create an agents.yml file to define your AI agents:

zookeeper:
  role: Zookeeper
  goal: Manage zoo operations
  backstory: >
    You are a seasoned zookeeper with a passion for wildlife conservation...

Tasks Configuration

Create a tasks.yml file to define the tasks for your agents:

write_stories:
  description: >
    Write an engaging zoo update capturing the day's highlights.
  expected_output: 5 engaging stories
  agent: zookeeper
  output_file: zoo_report.md

Running the Server

After installation, you can run the MCP CrewAI server using one of these methods:

Standard Command

mcp-crew-ai --agents path/to/agents.yml --tasks path/to/tasks.yml

Using UV Execution

uvx mcp-crew-ai --agents path/to/agents.yml --tasks path/to/tasks.yml

Or run just the server:

uvx mcp-crew-ai-server

Command Line Options

The server accepts several command line arguments:

• --agents: Path to your agents YAML file (required)
• --tasks: Path to your tasks YAML file (required)
• --topic: Main topic for the crew to work on (default: "Artificial Intelligence")
• --process: Process type to use ("sequential" or "hierarchical", default: "sequential")
• --verbose: Enable detailed output
• --variables: JSON string or path to JSON file with additional variables
• --version: Display version information

Advanced Usage Examples

Using Variable Substitution

You can provide additional variables to be used in your YAML templates:

mcp-crew-ai --agents examples/agents.yml --tasks examples/tasks.yml --topic "Machine Learning" --variables '{"year": 2025, "focus": "deep learning"}'

This will replace placeholders in your YAML files. For example, {topic} will be replaced with "Machine Learning" and {year} with "2025".

Configuring Different Process Types

To use a hierarchical process instead of the default sequential one:

mcp-crew-ai --agents examples/agents.yml --tasks examples/tasks.yml --process hierarchical

This changes how the agents interact and complete the assigned tasks.

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.