Mcp Prefect

What is Mcp Prefect about?

Mcp Prefect implements a Model Context Protocol (MCP) server for Prefect, allowing AI assistants to perform common Prefect operations using natural‑language commands.

How to use Mcp Prefect?

1. Configure the Prefect connection via environment variables:

   export PREFECT_API_URL="http://localhost:4200/api"
   export PREFECT_API_KEY="your_api_key"
   

2. Start the server (the repository includes a Docker Compose setup):

   docker compose up
   

3. Connect an AI assistant that understands the MCP specification to the running server. The assistant can then issue commands such as "Show me all my flows" or "Trigger the 'data-processing' deployment".

Key Features

• Flow Management – list, retrieve, and delete flows.
• Flow Run Management – create, monitor, and control flow runs.
• Deployment Management – manage deployments and their schedules, including triggering and pausing.
• Task Run Management – observe and control individual task runs.
• Work Queue Management – create and administer work queues.
• Block Management – access block types and block documents.
• Variable Management – create and update Prefect variables.
• Workspace Management – retrieve workspace information.

Use Cases

• An AI‑powered chatbot helps data engineers quickly inspect the status of their pipelines without opening the Prefect UI.
• Automated monitoring agents query failed flow runs and raise alerts in Slack or email.
• Natural‑language driven orchestration scripts trigger deployments on demand (e.g., "Run the nightly ETL now").
• Self‑service portals allow non‑technical users to pause or resume schedules using plain English.

FAQ

Q: Do I need Prefect Cloud? A: No. The server works with any Prefect deployment reachable via PREFECT_API_URL; a Cloud API key is only required for Cloud instances.

Q: Can I extend the server with new Prefect APIs? A: Yes. Add the function to the appropriate module under src/mcp_prefect and include it in the get_all_functions() list. For new API categories, update APIType in enums.py and modify main.py.

Q: Which transport protocol is supported? A: The example configuration shows using Server‑Sent Events (--transport sse). Additional transports can be added as needed.

Q: How are environment variables passed to the server? A: They are set in the container or host environment before launching the server, as shown in the configuration step above.

Q: What if some endpoints are missing? A: The README notes that several endpoints are yet to be implemented; contributions are welcome to fill those gaps.

Prefect MCP Server

A Model Context Protocol (MCP) server implementation for Prefect, allowing AI assistants to interact with Prefect through natural language.

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

Set 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)

Usage

Run the MCP server, and prefect:

docker compose up

Example Input

Once connected, an AI assistant can help users interact with Prefect using natural language. Examples:

• "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?"

Development

Several of the endpoints have yet to be implemented

Adding New Functions

To add a new function to an existing API:

1. Add the function to the appropriate module in src/mcp_prefect
2. Add the function to the get_all_functions() list in the module

To add a new API type:

1. Add the new type to APIType in enums.py
2. Create a new module in src/prefect/
3. Update main.py to include the new API type

Example usage:

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