Prefect MCP server for AI agents

Prefect MCP Server is a Model Context Protocol implementation that enables AI assistants to interact with Prefect through natural language commands. This server bridges the gap between natural language queries and Prefect's API, allowing users to manage flows, deployments, and other Prefect resources using conversational instructions.

Features

This MCP server provides access to the following Prefect APIs:

Flow Management: List, get, and delete flows
Flow Run Management: Create, monitor, and control flow runs
Deployment Management: Manage deployments and their schedules
Task Run Management: Monitor and control task runs
Work Queue Management: Create and manage work queues
Block Management: Access block types and documents
Variable Management: Create and manage variables
Workspace Management: Get information about workspaces

Configuration

Before using the MCP server, you need to set up the following environment variables:

export PREFECT_API_URL="http://localhost:4200/api"  # URL of your Prefect API
export PREFECT_API_KEY="your_api_key"               # Your Prefect API key (if using Prefect Cloud)

Installation and Startup

The easiest way to run the MCP server is using Docker Compose:

docker compose up

This command starts both the Prefect API and the MCP server.

Using the MCP Server

Once the server is running, AI assistants can interact with Prefect using natural language commands. Here are some example queries you can use:

"Show me all my flows"
"List all failed flow runs from yesterday"
"Trigger the 'data-processing' deployment"
"Pause the schedule for the 'daily-reporting' deployment"
"What's the status of my last ETL flow run?"

Example Configuration

To configure your AI assistant to use this MCP server, you might need to provide configuration similar to:

{
  "mcpServers": {
    "mcp-prefect": {
      "command": "mcp-prefect",
      "args": [
        "--transport", "sse"
      ],
      "env": {
        "PYTHONPATH": "/path/to/your/project/directory"
      },
      "cwd": "/path/to/your/project/directory"
    }
  }
}

This configuration tells your AI assistant how to connect to and communicate with the MCP server, enabling it to interpret your Prefect-related requests and take appropriate actions.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-prefect" '{"command":"mcp-prefect","args":["--transport","sse"],"env":{"PREFECT_API_URL":"http://localhost:4200/api"}}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "mcp-prefect": {
            "command": "mcp-prefect",
            "args": [
                "--transport",
                "sse"
            ],
            "env": {
                "PREFECT_API_URL": "http://localhost:4200/api"
            }
        }
    }
}

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-prefect": {
            "command": "mcp-prefect",
            "args": [
                "--transport",
                "sse"
            ],
            "env": {
                "PREFECT_API_URL": "http://localhost:4200/api"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect