Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Roboflow with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Manage computer vision workflows. upload images, train models, and manage datasets directly from your AI agent.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 29 capabilities

The complete Roboflow capability set.

These are the exact actions your AI can choose when you ask it to work with Roboflow.

Capability set01 / 08

01-04

4 capabilities in this set.

Part of 29 available through Roboflow.

  1. 01

    Add projects to folder

    Add projects to a folder (Enterprise)

  2. 02

    Auto label

    Start an auto-labeling job using foundation models

  3. 03

    Create project

    Create a new project in a workspace

  4. 04

    Delete images

    Delete multiple images from a project

Capability set02 / 08

05-08

4 capabilities in this set.

Part of 29 available through Roboflow.

  1. 05

    Delete project

    Delete a project or version (moves to Trash)

  2. 06

    Fork universe project

    Fork a public project from Roboflow Universe

  3. 07

    Get async task

    Track long-running operations like forking or large exports

  4. 08

    Get project

    Get project details, metadata, and versions

Capability set03 / 08

09-12

4 capabilities in this set.

Part of 29 available through Roboflow.

  1. 09

    Get root

    Verify authentication and retrieve default workspace

  2. 10

    Get version

    Retrieve metadata for a specific dataset version

  3. 11

    List folders

    List project folders in a workspace (Enterprise)

  4. 12

    List workspace projects

    List information about a workspace and its projects

Capability set04 / 08

13-16

4 capabilities in this set.

Part of 29 available through Roboflow.

  1. 13

    Restore trash

    Restore an item from the trash

  2. 14

    Run inference

    Run inference on an image using hosted models

  3. 15

    Search workspace images

    Search and filter images within a workspace

  4. 16

    Start training

    Start training a model on a dataset version

Capability set05 / 08

17-20

4 capabilities in this set.

Part of 29 available through Roboflow.

  1. 17

    Upload annotation

    Attach an annotation file to an existing image

  2. 18

    Upload image

    Upload an image to a project

  3. 19

    Cancel training

    Cancel an active training job

  4. 20

    Create annotation job

    Assign a batch of images to a labeler and reviewer

Capability set06 / 08

21-23

3 capabilities in this set.

Part of 29 available through Roboflow.

  1. 21

    Create folder

    Create a project folder (Enterprise)

  2. 22

    Download dataset

    Retrieve a download link for a zipped dataset in a specific format

  3. 23

    Get dataset health

    Check dataset health (class distribution, missing annotations, etc)

Capability set07 / 08

24-26

3 capabilities in this set.

Part of 29 available through Roboflow.

  1. 24

    Get image

    Get details for a specific image

  2. 25

    Get training results

    Retrieve metrics and status for a version training run

  3. 26

    List trash

    List items in the workspace trash

Capability set08 / 08

27-29

3 capabilities in this set.

Part of 29 available through Roboflow.

  1. 27

    Manage image tags

    Add, remove, or set tags on an image

  2. 28

    Search project images

    Search and filter images within a specific project

  3. 29

    Stop training

    Early stop an active training job

Observed, not estimated

1194ms average. Fast in production.

Roboflow is checked daily against the live service.

Daily averagePeak 1449ms
Aug 20Today
Fastest day
997ms
Slowest day
1449ms
14-day trend
Slowing+6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 29 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Roboflow, so you can see the experience inside your AI.

It does not authenticate your account with Roboflow. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Roboflow Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Roboflow capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "roboflow-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Roboflow owners ask.

  • 01

    How can I verify if my Roboflow API key is correctly configured?

    You can use the get_root capability. It will attempt to authenticate with your key and return the default workspace details if successful.

  • 02

    Can I get the training performance metrics for a specific model version?

    Yes! Use the get_training_results capability by providing the workspace, project, and version ID. It returns mAP, precision, recall, and other training metrics.

  • 03

    Is it possible to export my dataset to a specific format like YOLOv5?

    Absolutely. Use the download_dataset capability and specify the format parameter (e.g., 'yolov5pytorch') to receive a download link for your zipped dataset.

Explore

More in Developer Tools

Suggestions