What are the runtime requirements for Prefect MCP Server?
You need Python 3.9 or newer, a virtual environment tool like `uv`, and Prefect 3 installed. The server runs via `uvx` and requires the `prefect-mcp-server` package.
@MCP-Mirror
基本信息
Mirror of
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"fortunto2_prefect-mcp-server": {
"command": "uv",
"args": [
"venv",
"--python",
"3.12",
"&&",
"source",
".venv/bin/activate"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Prefect MCP Server is an MCP server that connects the Prefect workflow orchestration platform to MCP-compatible clients, primarily the Cursor IDE. It enables developers to interact with Prefect directly from their development environment using the Model Context Protocol.
Install via uv pip install -U prefect-mcp-server, configure the server in .cursor/mcp.json with the uvx command, and set environment variables like PREFECT_API_URL. The server then runs automatically within Cursor or can be started manually with uv run.
uvx for consistent environment handling.cursor/mcp.json in Cursor IDEPREFECT_API_KEY environment variableYou need Python 3.9 or newer, a virtual environment tool like `uv`, and Prefect 3 installed. The server runs via `uvx` and requires the `prefect-mcp-server` package.
Configuration is done via a `.cursor/mcp.json` file that sets the command to `uvx` with arguments `["prefect-mcp-server"]`. Environment variables such as `PREFECT_API_URL` and optionally `PREFECT_API_KEY` are set in a `.env` file.
The server uses standard MCP transport over stdio, invoked via the `uvx` command as defined in the Cursor MCP configuration.
Authentication is handled through the `PREFECT_API_KEY` environment variable, which can be set in the `.env` file to connect to Prefect Cloud or a Prefect server.
The complete list of available tools and their parameters is documented in the `docs/prefect_mcp_documentation.md` file included in the repository.
🚀 The fast, Pythonic way to build MCP servers and clients.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Painless E2E Automation for Mobile and Web
Open-source MCP to use Blender with any LLM
A search tool helps dev to solve the naming things problem.
评论