Roboflow + Cursor

Manage datasets, train models, build Workflows and run inference in Roboflow from Cursor, with the Roboflow plugin and MCP server.

Cursor is an AI code editor. The Roboflow plugin on the Cursor marketplace adds Roboflow's hosted MCP server and Skills, task guides the agent reads as it works, so Cursor can use your Roboflow workspace while you code.

Install the plugin, sign in to Roboflow, and ask Cursor's agent in plain language. It can work with your datasets and annotations, train and evaluate models, build Workflows, run inference, and write the code that calls your model from your app.

How to connect Cursor to Roboflow

5 steps
  1. Open the Roboflow plugin listing

    Go to the Roboflow plugin on the Cursor marketplace, or run /add-plugin roboflow in Cursor.

  2. Sign in and add the plugin

    Sign in to Cursor if prompted and confirm the install. This adds the Roboflow MCP server and Skills.

  3. Authorize Roboflow

    The first time Cursor connects, Roboflow opens in your browser so you can sign in and authorize it.

  4. Check the connection

    Ask Cursor's agent to list the projects in your Roboflow workspace.

  5. Ask Cursor to build

    Ask it to run a model on your images, train a model, build a Workflow, or add inference code to your app.

What teams build with Cursor

  • Add vision to an app you're building

    Have Cursor write the code that calls your Roboflow model, right in your project.

  • Train a model without leaving the editor

    Manage your dataset and versions, then train a model and check its evaluation results.

  • Build a Workflow from a description

    Describe the pipeline and let Cursor build and save the Workflow.

Questions

No. Cursor connects with OAuth and signs in with your Roboflow account in the browser.

Yes. Put the server in .cursor/mcp.json at the project root instead of your global config. The server URL is https://mcp.roboflow.com/mcp.

No. The MCP server and Skills have no extra cost. You pay only for the Roboflow usage behind them on your plan.

Why are companies choosing Roboflow?

The end-to-end platform for vision AI: create datasets, train models and deploy to production.

  • Flexible deployment modes

    Move from a scalable cloud API to edge hardware like NVIDIA Jetson without managing complex dependencies.

  • Integrated workflow builder

    Combine multiple AI models, custom business logic and third-party integrations into one production-ready pipeline in a low-code editor.

  • Model monitoring and alerts

    Dashboards track confidence, inference time and request volume for your deployed models, and email alerts tell your team when confidence suddenly drops.

View all
Get started

Build on the Platform

For developers, engineers, and technical founders who want to get hands on. Try the free tier; the docs are open.

Bring it into your operation

For heads of AI, operations leaders, and enterprise teams. Bring a known problem, or work with us to find the first one worth taking on.