Roboflow + Claude

Manage datasets, train models, build Workflows and run inference in Roboflow by asking Claude, with Roboflow connected from the Claude directory.

Claude is Anthropic's AI assistant, on desktop, web and mobile. Roboflow's listing in the Claude directory connects Claude to Roboflow's hosted MCP server and Skills, task guides Claude reads as it works, so Claude can use your Roboflow workspace.

Connect Roboflow, sign in, and ask in plain language. Claude can work with your datasets and annotations, train and evaluate models, build Workflows, and run inference on your images.

How to connect Claude to Roboflow

5 steps
  1. Open the Roboflow listing

    Go to Roboflow in the Claude directory, or click Add to Claude on roboflow.com/mcp.

  2. Select Connect

    Select Connect to add Roboflow to your Claude account.

  3. Sign in to Roboflow

    Roboflow opens in your browser so you can sign in and authorize Claude.

  4. Check the connection

    In a new chat, ask Claude to list the projects in your Roboflow workspace.

  5. Ask Claude to build

    Ask it to find a dataset, train a model, build a Workflow, or run a model on your images.

What teams build with Claude

  • Run a model on an image from your phone

    Ask Claude on mobile to run your Roboflow model on a photo you just took.

  • Train a model in a conversation

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

  • Build a Workflow from a description

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

Questions

No. Claude connects with OAuth and you sign in with your Roboflow account.

Yes. Claude Code installs Roboflow as a plugin from the terminal, with the same MCP server and Skills.

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.