What is prefect_mcp_usage?

A set of instructions for connecting Cursor, a code editor, to Prefect through an MCP server. Prefect is a tool for running and monitoring Python workflows.

It helps list flows, find flows by name or ID, and inspect Prefect deployments and flow runs. It requires Python, Prefect, MCP tools, Cursor, and a configured Prefect API connection.

It gives the coding agent a defined way to work with Prefect instead of requiring manual API requests or dashboard use.

prefect_mcp_usage — Cursor rule for Cursor by fortunto2: A set of instructions for connecting Cursor, a code…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add rules/fortunto2/prefect-mcp-server/prefect_mcp_usage

Clone the repo

git clone --depth 1 https://github.com/fortunto2/prefect-mcp-server

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/rules/fortunto2/prefect-mcp-server/prefect_mcp_usage.svg)](https://agentmods.dev/rules/fortunto2/prefect-mcp-server/prefect_mcp_usage)

Your own site

<a href="https://agentmods.dev/rules/fortunto2/prefect-mcp-server/prefect_mcp_usage"><img src="https://agentmods.dev/badge/rules/fortunto2/prefect-mcp-server/prefect_mcp_usage.svg" alt="Measured on agentmods" height="20"></a>

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 725 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00005	$0.00725
Opus 5	$0.00003	$0.00362
Sonnet 5	$0.00001	$0.00145
Haiku 4.5	$0.00001	$0.00072

Measured 5d ago against content hash 418c115f7514, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

prefect_mcp_usage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/prefect_mcp_usage.mdc · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prefect MCP Server Usage with Cursor

Overview

This rule provides guidance on how to work with the Prefect MCP server in the Cursor IDE, incorporating the Model Context Protocol (MCP) to interact with Prefect workflows, deployments, and flow runs.

Prerequisites

Python 3.10 or higher
Prefect 3.0+ installed
MCP CLI tools installed
Cursor IDE

Setup Environment

Installation

Install the required packages:

uv pip install prefect-mcp-server mcp[cli] prefect>=3.0.0

Environment Variables

Configure the Prefect API connection:

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

Running the Prefect MCP Server

There are multiple ways to run the Prefect MCP server:

From Command Line

prefect-mcp-server

Using MCP Dev

For development and testing:

mcp dev prefect_mcp_server_pkg/server.py

Integration with Cursor

Cursor supports MCP tools, allowing you to interact with the Prefect API through the Prefect MCP server.

Available Tools

The server provides tools for:

Flow Management

Get flow by ID (get_flow_by_id)
Get flow by name (get_flow_by_name)
List flows (list_flows)
Search flows (search_flows)

Flow Run Operations

Get flow run by ID (get_flow_run_by_id)
List flow runs (list_flow_runs)
Search flow runs by state (search_flow_runs_by_state)
Cancel flow run (cancel_flow_run)

Deployment Operations

Get deployment by ID (get_deployment_by_id)
Get deployment by name (get_deployment_by_name)
List deployments (list_deployments)
Search deployments by status (search_deployments_by_status)
Create flow run from deployment (create_flow_run_from_deployment)

Using in Cursor

Cursor supports MCP tools natively, allowing you to interact with your Prefect workflows directly from the editor.

Example Usage

Start the Prefect MCP server
Open Cursor IDE
Connect to the MCP server (usually automatic if running locally)
Use the available tools through Claude AI integration in Cursor

Read the full file on GitHub · 126 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 126 lines · 5 tokens per session scan A 418c115f7514

Subscribe to this mod's changes

prefect_mcp_usage is a cursor rule published in the GitHub repository fortunto2/prefect-mcp-server (7 stars, last pushed 11mo ago), licensed MIT. It adds 5 tokens to every session and 725 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Backend and APIs

prefect_mcp_usage