# Roboflow — how to use (mcp.ai)

Connect your Roboflow account and use 7 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Build and use computer vision models fast with Roboflow. Train, deploy, and run inference on object detection, classification, and segmentation models.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_roboflow?ms=1787295780000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `roboflow_describe_workflow_interface`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/roboflow`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/roboflow/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/roboflow/describe/workflow/interface` — Tool to describe the interface of a workflow specification. Use when you need to understand the inputs, outputs, and types for a Roboflow workflow definition.
  - body: { api_key: string, specification: object }
- `POST https://api.mcp.ai/api/roboflow/get/execution/engine/versions` — Tool 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.
- `POST https://api.mcp.ai/api/roboflow/get/server/info` — Tool to retrieve information about the Roboflow inference server. Use when you need to check the server version, name, or unique identifier.
- `POST https://api.mcp.ai/api/roboflow/get/server/metrics` — Tool to retrieve Prometheus metrics from the Roboflow inference server. Use when monitoring server performance, tracking inference statistics, or debugging server health issues.
- `POST https://api.mcp.ai/api/roboflow/get/workflow/schema` — Tool to fetch the workflows block schema from Roboflow. Use when you need to retrieve the complete schema definition for workflow blocks.
- `POST https://api.mcp.ai/api/roboflow/run/workflow` — Tool 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.
  - body: { inputs: object, api_key?: string, is_preview?: boolean, workflow_id?: string, specification: object, excluded_fields?: string[], enable_profiling?: boolean }
- `POST https://api.mcp.ai/api/roboflow/validate/workflow` — Tool to validate a Roboflow workflow specification before execution. Use this to check if your workflow definition is syntactically correct and properly structured.
  - body: { steps: object[], inputs: object[], api_key?: string, outputs: object[], version: string }

## Example prompts
- "What can I do in Roboflow?"
- "Show me a summary of my Roboflow account"

## More
- Page: https://mcp.ai/roboflow
- Agent spec (llms.txt): https://mcp.ai/roboflow/llms.txt
- Postman collection: https://mcp.ai/roboflow/postman.json