How to connect Roboflow to ChatGPT

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 a custom MCP server

   On ChatGPT web, open Plugins, select +, then Add custom MCP server.

3. 3. Paste your Metorial MCP URL

   Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>), choose OAuth and accept the risk notice.

4. 4. Create and install the plugin

   Select Create as a plugin, install it 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.

• Type @ and pick the plugin. The selection applies to that message only, so @mention it again when a follow-up needs fresh Roboflow data.
• For write actions, ChatGPT may ask you to confirm first, depending on the app permissions and the action.
• Once published for a workspace, ChatGPT keeps a snapshot of the tool list. When your team adds Roboflow tools in Metorial, an admin refreshes the actions in Workspace settings before they appear.
• You can use several apps in one prompt, for example read Roboflow data and then create a ticket in another app.

Add custom MCP server is missing

Workspace policy controls it. On Enterprise and Edu, an admin grants the permission to create plugins with MCPs; ask them to enable it for you.

The plugin exists but no tools appear

Creating the plugin is not enough: install it from your plugins, then start a new conversation so ChatGPT loads its tools.

ChatGPT answers without using the tools

Pick the plugin with @ in the composer and name the action you want, for example "use Metorial to look up the latest ticket".

Based on the ChatGPT MCP documentation.