Integration

Roboflow integration

Computer vision platform for building and deploying object detection, classification, and segmentation models. Upload images, annotate datasets, train models, and run inference with a simple API.

Connect Roboflow How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Roboflow.Built from the 8 Roboflow tools below, on the connection you add once.

Common Roboflow use cases

Project info
Auto-labeling
Training export
Dataset building
Model evaluation
Object detection
Project overview
Dataset discovery
Version info
Data collection

What you can do with Roboflow

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Project, 2 operations

get_projectGet projectGETRetrieves project details and versions.
list_projectsList projectsGETLists all projects in a workspace.

Annotation, 1 operation

annotate_imageAnnotate imagePOSTAdds bounding box annotations to an image.

Dataset, 1 operation

export_datasetExport datasetGETExports dataset in specified annotation format.

Image, 1 operation

upload_imageUpload imagePOSTUploads an image to a Roboflow dataset.

Prediction, 1 operation

inferInferPOSTRuns inference on an image using a trained model.

Universe, 1 operation

search_universeSearch universeGETSearches Roboflow Universe for public datasets.

Version, 1 operation

get_versionGet versionGETRetrieves details of a specific model version.

Use Roboflow from Claude Code, Cursor or Codex

Connect Roboflow in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Roboflow operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Roboflow

Create your workspace
Sign up free. Nothing to install.
Connect Roboflow once
Add your Roboflow connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Roboflow integration FAQ

What can you do with the Roboflow integration?

LiveContext exposes 8 operations on Roboflow, covering project, annotation, dataset and image. Common uses include Project info, Auto-labeling and Training export.