MCP For Claude Marketplace
Roboflow

Roboflow MCP Connector for Claude

A+

Manage computer vision workflows — upload images, train models, and manage datasets directly from your AI agent.

29 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect Roboflow to your AI agent to streamline your computer vision pipeline. From dataset management to model training and inference, handle your entire CV lifecycle through natural language.

What you can do

  • Workspace & Project Management — List projects, create new ones, or fork from Roboflow Universe to jumpstart your development.
  • Dataset Operations — Upload images (via URL or Base64), manage versions, and download datasets in various formats like COCO or YOLO.
  • Model Training — Start training runs, monitor results, and retrieve precise performance metrics (mAP, precision, recall) for any version.
  • Image Search — Search and filter images within your workspace to audit your data and improve model accuracy.
  • Inference & Results — Run inference on images and retrieve results to verify model behavior in real-time.

How it works

  1. Subscribe to this server
  2. Enter your Roboflow Private API Key
  3. Start building and managing vision models from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • ML Engineers — monitor training progress and dataset health without leaving the terminal or IDE.
  • Data Scientists — quickly query dataset versions and export data for custom training scripts.
  • Product Teams — audit model performance and visualize inference results through simple conversation.
computer-visiondataset-managementmodel-trainingimage-annotationmachine-learningworkflow-automation

29 tools expose this connector's capabilities to your AI agent.

add_projects_to_folder

Add projects to a folder (Enterprise)

auto_label

Start an auto-labeling job using foundation models

cancel_training

Cancel an active training job

create_annotation_job

Assign a batch of images to a labeler and reviewer

create_folder

Create a project folder (Enterprise)

create_project

Create a new project in a workspace

delete_images

Delete multiple images from a project

delete_project

Delete a project or version (moves to Trash)

download_dataset

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

fork_universe_project

Fork a public project from Roboflow Universe

get_async_task

Track long-running operations like forking or large exports

get_dataset_health

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

get_image

Get details for a specific image

get_project

Get project details, metadata, and versions

get_root

Verify authentication and retrieve default workspace

get_training_results

Retrieve metrics and status for a version training run

get_version

Retrieve metadata for a specific dataset version

list_folders

List project folders in a workspace (Enterprise)

list_trash

List items in the workspace trash

list_workspace_projects

List information about a workspace and its projects

manage_image_tags

Add, remove, or set tags on an image

restore_trash

Restore an item from the trash

run_inference

Run inference on an image using hosted models

search_project_images

Search and filter images within a specific project

search_workspace_images

Search and filter images within a workspace

start_training

Start training a model on a dataset version

stop_training

Early stop an active training job

upload_annotation

Attach an annotation file to an existing image

upload_image

Upload an image to a project

See how to talk to your AI agent using Roboflow.

List all projects in my Roboflow workspace 'industrial-safety'.

I've retrieved the projects for 'industrial-safety'. You have 3 active projects: 'Hard Hat Detection' (object-detection), 'Glove Compliance' (classification), and 'Forklift Tracking'. Which one would you like to inspect?

Upload this image URL to the 'Hard Hat Detection' project in workspace 'industrial-safety'.

Uploading image... Success! The image has been added to the 'Hard Hat Detection' project. It is currently in the unassigned batch. Would you like to assign it to a specific split?

Show me the training metrics for version 5 of the 'Forklift Tracking' project.

Fetching results for version 5... The model achieved a mAP of 88.5%, with a precision of 91.2% and recall of 84.7%. The training run is completed. Would you like to see the full metrics breakdown?

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

Related Connectors

KE

Kentico (CMS & DXP) MCP

10 tools Official

Manage content and system objects via Kentico Xperience — retrieve documents, manage users, and audit custom tables.

A+ View details →
BS

Brawl Stars MCP

10 tools Official

Access real-time Brawl Stars data — track player stats, battle logs, club rankings, and event rotations directly from your AI agent.

F View details →
MY

MyJohnDeere MCP

6 tools Official

Manage agricultural operations via MyJohnDeere — list organizations, equipment assets, fields, and machine telematics directly from any AI agent.

A+ View details →
FI

FireHydrant MCP

12 tools Official

Manage incidents, services, and responder teams via AI agents with FireHydrant.

A+ View details →