Roboflow MCP: computer vision for your coding agent

Connect Roboflow to Claude Code, Cursor or ChatGPT

1. 1Click Connect Roboflow free and sign in with your Roboflow account.
2. 2Every tool is on after you connect. Keep the inference and Workflow tools; if the list includes training or dataset changes you'd rather handle yourself, switch those off.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app to validate a Roboflow Workflow and run it on a sample image, then open Activity to see both calls.

Computer vision work from your editor

• Work with datasets, annotation and dataset versions.
• Train models and run inference for object detection, classification and segmentation.
• Describe a Workflow's inputs and outputs, validate it, then run it with your inputs.
• Check the inference server's version and its Prometheus metrics.

Training and data under watch

• Switch off any Roboflow tool you don't want your AI app to call; it's hidden and refused if called.
• Use a policy to warn before calls that change datasets or start training.
• Activity records every Workflow run and inference call.

What you get with Roboflow and ContextGate

• Your AI apps can use RoboflowClaude, Cursor, ChatGPT and other AI apps reach Roboflow through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Roboflow tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Roboflow tools

Examples of what your AI apps can do in Roboflow. You'll see the exact list of tools after you connect it.

• Get Workflow SchemaTool to fetch the workflows block schema from Roboflow. Use when you need to retrieve the complete schema definition for workflow blocks.
• Run WorkflowTool to run a workflow specification with provided inputs. Use when you need to execute a custom Roboflow workflow pipeline for image processing, model inference, or other computer vision tasks.
• Describe Workflow InterfaceTool to describe the interface of a workflow specification. Use when you need to understand the inputs, outputs, and types for a Roboflow workflow definition.
• Get Execution Engine VersionsTool to retrieve available Execution Engine versions from Roboflow workflows API. Use when you need to check which execution engine versions are supported for workflow processing.
• Get Server InfoTool to retrieve information about the Roboflow inference server. Use when you need to check the server version, name, or unique identifier.
• Get Server MetricsTool to retrieve Prometheus metrics from the Roboflow inference server. Use when monitoring server performance, tracking inference statistics, or debugging server health issues.
• Validate WorkflowTool to validate a Roboflow workflow specification before execution. Use this to check if your workflow definition is syntactically correct and properly structured.