How to connect Roboflow to Claude Code

1. 1. Enable Roboflow in Metorial

   In your Metorial portal, enable the Roboflow MCP server and sign in with the account that owns the data. Access stays governed by your team policies.

2. 2. Add the server over HTTP

   Add --scope user to use it in every project.

   Copy

   claude mcp add --transport http metorial <your-magic-mcp-url>

3. 3. Sign in

   Run /mcp, select Metorial and sign in to load Roboflow tools.

• List Annotation Jobs: List all annotation jobs for a project.
• Upload Annotation: Upload an annotation file for a specific image in a project.
• Run Inference: Run predictions on an image using a trained model deployed on the Roboflow hosted inference API.
• Create Annotation Job: Create a new annotation job for a project.
• Get Project: Get detailed information about a specific Roboflow project, including its dataset versions, annotation classes, image splits, and training status.
• Train Model: Start training a model on a specific dataset version using Roboflow Train.
• List Projects: List all projects in a Roboflow workspace.
• Export Dataset: Export a dataset version as a downloadable ZIP in a specified annotation format.
• Get Image: Get detailed information about a specific image in a project, including its annotations, labels, tags, split assignment, and URLs for the original and thumbnail versions.
• Delete Images: Delete one or more images from a Roboflow project.
• Create Project: Create a new computer vision project in the workspace.
• Create Version: Generate a new versioned snapshot of a project's dataset with optional preprocessing and augmentation settings.
• Search Images: Search for images within a project using text prompts, visual similarity to an existing image, or by filtering on tags, classes, and batch assignments.
• Upload Image: Upload an image to a Roboflow project.
• Get Version: Get detailed information about a specific dataset version, including preprocessing and augmentation settings, training results (mAP, precision, recall), and model endpoint details.
• And 6 more on the Roboflow MCP server page.

• Roboflow tools appear as mcp__metorial__<tool>. Use that name in permission rules to allow or deny a tool.
• Run /mcp to see whether Metorial is connected and to sign in again.
• Claude Code warns when a tool result passes 10,000 tokens and caps it at 25,000 by default. Raise the cap with MAX_MCP_OUTPUT_TOKENS.
• Pre-approve trusted Roboflow tools with allow rules in your settings so Claude Code stops asking each time.

claude mcp list shows "Needs authentication"

Run /mcp, select Metorial, and sign in. If sign-in keeps failing, choose Clear authentication in the same menu and sign in again.

A teammate sees "Pending approval"

Servers shared through a project .mcp.json need approval. Run claude in the project and approve Metorial when asked.

Large tool results are cut off

Claude Code limits MCP tool output to 25,000 tokens by default. Raise it with the MAX_MCP_OUTPUT_TOKENS environment variable.

Based on the Claude Code MCP documentation.