Roboflow Connector for AI agents.

29 live capabilities

Manage computer vision datasets and train models directly from your chat.

Live agent request Roboflow / Connector

Waiting for input…

AI Agent

Why people use Roboflow

Roboflow for Computer Vision Dataset Management

This Connector lets you do all of that through a single chat. You can ask your agent to upload images from a URL, create new projects, or audit your dataset health in seconds. It turns a multi-tab chore into a few quick commands, letting you stay focused on building your model.

What Vinkius changes

You get a direct way to manage your Roboflow account inside your favorite AI chat.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

Real-world use case 01

Auditing dataset balance

An ML engineer needs to check if a dataset is balanced.
Real-world use case 02

Starting a training run

A data scientist wants to quickly start a training run.
Real-world use case 03

Testing model behavior

A developer needs to test a model's accuracy on a new image.

Complete set · 29capabilities

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.

01 Capability
Add projects to folder
Move projects into specific folders within your workspace. This is useful for organizing large-scale enterprise environments.
02 Capability
Auto label
Start an auto-labeling job using foundation models. This helps you label massive datasets much faster than doing it manually.
03 Capability
Cancel training
Stop an active training job immediately. Use this if you notice a model is diverging or you need to restart with different parameters.
04 Capability
Create annotation job
Assign a batch of images to a human labeler or reviewer. This helps manage your manual labeling workflow efficiently.

Capability set02 / 08

05—08

4 capabilities in this set.

Part of 29 available through Roboflow.

05 Capability
Create project
Start a new project within your workspace. You can set up the initial metadata and categories in one go.
06 Capability
Delete images
Remove multiple images from a project at once. This is great for cleaning up bad data or duplicates.
07 Capability
Delete project
Move a project or a specific version to the trash. It keeps your workspace clean without permanent deletion.
08 Capability
Download dataset
Get a direct download link for a zipped dataset in formats like COCO or YOLO. This makes it easy to move data to your local machine.

Capability set03 / 08

09—12

4 capabilities in this set.

Part of 29 available through Roboflow.

09 Capability
Fork universe project
Copy a public project from Roboflow Universe into your own workspace. It's a fast way to start from a pre-built model.
10 Capability
Get async task
Track the status of long-running operations like large exports or forking. This lets you know when your task is actually finished.
11 Capability
Get image
Pull the specific details and metadata for a single image. Use this to inspect individual data points in your project.
12 Capability
Get project
Fetch all details, metadata, and versions for a specific project. It gives your agent the full context of your work.

Capability set04 / 08

13—16

4 capabilities in this set.

Part of 29 available through Roboflow.

13 Capability
Get root
Verify your API key and find your default workspace. This is the first step to ensuring your connection is active.
14 Capability
Get training results
Pull the status and metrics for a specific training run. You can see mAP, precision, and recall directly in your chat.
15 Capability
Get version
Retrieve the metadata for a specific dataset version. This is helpful when you need to know exactly what's in a specific release.
16 Capability
List folders
See all project folders in your workspace. This is a required step for managing organized enterprise environments.

Capability set05 / 08

17—20

4 capabilities in this set.

Part of 29 available through Roboflow.

17 Capability
List trash
View the items currently in your workspace trash. You can see what you've deleted recently to ensure nothing was lost.
18 Capability
List workspace projects
Get a list of all projects and their info in a workspace. This gives you a high-level view of your entire portfolio.
19 Capability
Manage image tags
Add, remove, or update tags on your images. This helps you organize your data for specific search queries.
20 Capability
Restore trash
Bring an item back from the trash to your workspace. Use this if you accidentally deleted a project or version.

Capability set06 / 08

21—23

3 capabilities in this set.

Part of 29 available through Roboflow.

21 Capability
Run inference
Send an image to a hosted model to see what it detects. This is perfect for quick testing of your model's behavior.
22 Capability
Search project images
Filter and find specific images within a single project. This helps you find specific examples of objects or errors.
23 Capability
Search workspace images
Search through all images across your entire workspace. It's the fastest way to find specific data points across multiple projects.

Capability set07 / 08

24—26

3 capabilities in this set.

Part of 29 available through Roboflow.

24 Capability
Start training
Begin a training run on a specific dataset version. You can trigger this via natural language to start your model development.
25 Capability
Upload annotation
Attach a new annotation file to an image that already exists. This is how you update labels for specific images.
26 Capability
Upload image
Send a new image to a project in your workspace. You can provide a URL or a Base64 string to get the data into Roboflow.

Capability set08 / 08

27—29

3 capabilities in this set.

Part of 29 available through Roboflow.

27 Capability
Create folder
Create a new project folder in your workspace. It helps keep your enterprise projects neatly categorized.
28 Capability
Get dataset health
Check your class distribution and find missing annotations. It helps you spot imbalances in your training data quickly.
29 Capability
Stop training
End an active training job early. Use this to save on compute costs if the model isn't improving as expected.

Set up in minutes

One URL. Then ask Roboflow to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Roboflow from the conversation.

Choose your client

Live preview

Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp

Step 01

Open Connectors

In Claude Web or Claude Desktop, open Settings and choose Connectors.
Step 02

Add the URL

Choose Add custom connector, name it Roboflow, and paste the URL above.
Step 03

Turn it on in chat

Select +, open Connectors, and enable Roboflow for the conversation.

ChatGPT · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp

Step 01

Open MCP settings

On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
Step 02

Add the URL

Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Roboflow URL.
Step 03

Save and start

Save the connection and enable Roboflow in your conversation. Desktop may ask you to restart once.

Cursor · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "roboflow": {
      "url": "https://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp"
    }
  }
}

Step 01

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
Step 02

Add the server config

Paste the JSON configuration above into the mcp.json file that opens
Step 03

Save the file

Cursor will automatically detect the new Connector
Step 04

Start using Roboflow

Open Agent mode in chat and ask: "Using Roboflow, help me...". 29 tools available

VS Code Copilot · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "roboflow": {
      "url": "https://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp"
    }
  }
}

Step 01

Create MCP config

Create a .vscode/mcp.json file in your project root
Step 02

Add the server config

Paste the JSON configuration above
Step 03

Enable Agent mode

Open GitHub Copilot Chat and switch to Agent mode using the dropdown
Step 04

Start using Roboflow

Ask Copilot: "Using Roboflow, help me...". 29 tools available

Windsurf · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "roboflow": {
      "url": "https://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp"
    }
  }
}

Step 01

Open MCP Settings

Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
Step 02

Add the server

Paste the JSON configuration above into mcp_config.json
Step 03

Save and reload

Windsurf will detect the new server automatically
Step 04

Start using Roboflow

Open Cascade and ask: "Using Roboflow, help me...". 29 tools available

Cline · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "roboflow": {
      "url": "https://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp"
    }
  }
}

Step 01

Open Cline MCP Settings

Click the Connectors icon in the Cline sidebar panel
Step 02

Add remote server

Click "Add Connector" and paste the configuration above
Step 03

Enable the server

Toggle the server switch to ON
Step 04

Start using Roboflow

Ask Cline: "Using Roboflow, help me...". 29 tools available

Claude Code · Terminal command

Official guide ↗

Advanced setup

claude mcp add roboflow --transport http "https://edge.vinkius.com/vk_preview_3PcAB3lxgco6m9RlryrdB51L1KU7rDlnqGHOwOaP/mcp"

Step 01

Install Claude Code

Run npm install -g @anthropic-ai/claude-code if not already installed
Step 02

Add the Connector

Run the command above in your terminal
Step 03

Verify the connection

Run claude mcp to list connected servers, or type /mcp inside a session
Step 04

Start using Roboflow

Ask Claude: "Using Roboflow, show me...". 29 tools are ready

Where the request belongs

Work Roboflow can move forward.

Built around the request

This is for the ML engineer who's tired of clicking through a dozen tabs to check a single training metric, or the data scientist who needs to quickly export specific dataset versions for a custom script.

01

ML Engineer

Monitors training progress and audits dataset health while staying inside the IDE.

02

Data Scientist

Queries version metadata and manages image uploads for training runs.

03

Product Manager

Checks model inference results and visualizes performance without needing to touch the code.

Build the capability set

Each Connector adds new actions and data without changing how you work.

Browse Connectors

01 10 capabilities

SigmaMind AI

Train custom computer vision models with your own images and deploy object detection and classification without ML expertise.

02 6 capabilities

Clarifai (Vision AI)

Manage AI inference via Clarifai. list apps, models, and workflows, and perform computer vision predictions directly from any AI agent.

03 11 capabilities

Scale AI

Automate high-quality data labeling and RLHF workflows via Scale AI. create projects, manage batches, and submit annotation tasks directly from your AI agent.

04 9 capabilities

NVIDIA Vision

Generate images, analyze visuals, detect objects, and caption images via NVIDIA Vision APIs.

05 5 capabilities

Hugging Face Vision

Connect Hugging Face Vision to any AI agent via MCP.

06 5 capabilities

EyePop.ai

Add computer vision to your apps with pre-trained models for object detection, face recognition, and image classification.

Bring your own AI

Change the model, client or framework. Keep Roboflow connected.

Before you connect

Questions about Roboflow.

The practical details behind the request, access and result.

Can the Roboflow MCP help me manage my images?

Yes, it lets you upload images via URLs, search through your workspace, and add tags to organize your data.

How do I check my model's performance?

You can ask your agent to pull the training results for any specific version, which includes metrics like mAP, precision, and recall.

Can I use the Roboflow MCP to start training?

Yes, you can tell your agent to start a training run on a specific dataset version just by describing it.

Does the Roboflow MCP support auto-labeling?

It allows you to kick off auto-labeling jobs using foundation models to speed up your data preparation.

Can I organize my projects into folders?

Yes, if you have an enterprise account, you can use the Connector to create folders and move projects into them.

How do I find a specific image in my project?

You can ask your agent to search and filter images within a specific project or your entire workspace.

Can I download my datasets through the Connector?

Yes, the agent can retrieve a direct download link for a zipped dataset in formats like COCO or YOLO.

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.

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.

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.

One connection away

Give your agent a direct line to Roboflow.

Connect Roboflow once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available