Roboflow MCP Server + Skills

Computer vision for your coding agent.

Give your coding agent direct access to Roboflow. Train custom models, run inference, and manage datasets, all from a prompt.

Get started View Docs

Compatible with

Claude Code

Claude Code

Claude Code

Claude Code

Watch the demo

Install

One server. Every agent.

One hosted MCP server. One API key. Drop it into the agent of your choice.

You'll need an API key

Grab a workspace API key first.

One key gives your agent full access to MCP tools and Skills. Find it in your Roboflow account settings.

app.roboflow.com/settings/api

Recommend

Universal Installer

Run this command in your terminal (replace YOUR_ROBOFLOW_API_KEY with your actual key):

claude mcp add -s user roboflow \
  --transport http https://mcp.roboflow.com/mcp \
  --header "x-api-key: YOUR_ROBOFLOW_API_KEY" \
  --header "Accept: application/json, text/event-stream"

Can't run the installer? Install manually

{
  "mcpServers": {
    "roboflow": {
      "type": "http",
      "url": "https://mcp.roboflow.com/mcp",
      "headers": {
        "x-api-key": "YOUR_ROBOFLOW_API_KEY",
        "Accept": "application/json, text/event-stream"
      }
    }
  }
}

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "roboflow": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.roboflow.com/mcp",
        "--header",
        "x-api-key:YOUR_ROBOFLOW_API_KEY"
      ]
    }
  }
}

Can't run the installer? Install manually

{
  "mcpServers": {
    "roboflow": {
      "type": "http",
      "url": "https://mcp.roboflow.com/mcp",
      "headers": {
        "x-api-key": "YOUR_ROBOFLOW_API_KEY",
        "Accept": "application/json, text/event-stream"
      }
    }
  }
}

Add this to ~/.codex/config.toml:

[mcp_servers.roboflow]
url = "https://mcp.roboflow.com/mcp"

[mcp_servers.roboflow.http_headers]
x-api-key = "YOUR_ROBOFLOW_API_KEY"
Accept = "application/json, text/event-stream"

Can't run the installer? Install manually

{
  "mcpServers": {
    "roboflow": {
      "type": "http",
      "url": "https://mcp.roboflow.com/mcp",
      "headers": {
        "x-api-key": "YOUR_ROBOFLOW_API_KEY",
        "Accept": "application/json, text/event-stream"
      }
    }
  }
}

Add this to Cursor’s MCP config (~/.cursor/mcp.json):

{
  "mcpServers": {
    "roboflow": {
      "type": "http",
      "url": "https://mcp.roboflow.com/mcp",
      "headers": {
        "x-api-key": "YOUR_ROBOFLOW_API_KEY",
        "Accept": "application/json, text/event-stream"
      }
    }
  }
}

Can't run the installer? Install manually

{
  "mcpServers": {
    "roboflow": {
      "type": "http",
      "url": "https://mcp.roboflow.com/mcp",
      "headers": {
        "x-api-key": "YOUR_ROBOFLOW_API_KEY",
        "Accept": "application/json, text/event-stream"
      }
    }
  }
}

⌥ Open source: roboflow/computer-vision-skills

Tools

30 tools across 9 categories.

Once connected, your agent can call any of these directly. Each tool maps to a primitive in the Roboflow platform: the same ones you'd use in the dashboard or API.

Projects

Manage projects in your workspace.

projects_create

Images

Upload images to a project.

images_prepare_upload

images_prepare_upload_zip

images_upload_zip_status

Annotation

Save annotations to a project image.

annotations_save

Batch

Organize images into batches and create labeling jobs.

annotation_batches_list

annotation_batches_get

annotation_jobs_create

Versions

Create and inspect dataset versions.

versions_generate

versions_export

Models

Train models and monitor training progress.

models_get_training_status

Workflows

Build and execute inference pipelines.

workflows_create

workflows_update

workflow_blocks_list

workflow_blocks_get_schema

workflow_specs_validate

workflow_specs_run

Universe

Search public datasets on Roboflow Universe.

universe_search

Meta

Report issues or suggestions.

meta_feedback_send

Not using MCP? Roboflow also ships a full CLI and REST API.

Skills

Expert knowledge, exposed to your agent.

Skills are markdown playbooks your agent reads as MCP resources. They cover auth, dataset organization, deployment choices, training playbooks, and where things live in the Roboflow app. Connected clients pick the right Skill for the task at hand.

HOW SKILLS WORK

Skills load when your agent needs them. No setup on your end.

Once your agent is connected to mcp.roboflow.com, it can list and read every Skill alongside its 30 tools. Prefer it offline? Install the bundle locally:

$

npx @roboflow/skills install

01

api-reference

Reference for the Roboflow REST and Inference APIs, including routes, hosts, auth, and request/response formats.

inference

rest-api

02

data-management

Use when uploading images, labeling, organizing datasets, creating Roboflow projects (detection / segmentation / keypoint / classification), tags, splits, versions, or RoboQL search.

labeling

03

inference

Use when running Roboflow model inference or choosing deployment (serverless, dedicated, self-hosted, batch). Prefers Workflows over direct model calls.

workflow-templates

workflows

04

plans-and-pricing

Use when answering questions about Roboflow plans, credit usage, or cost estimation. Directs users to roboflow.com/pricing for current dollar amounts.

plans

pricing

05

product-navigation

Use when explaining where Roboflow features live in the app.roboflow.com web app — maps intents like upload, annotate, train, deploy to specific page URLs.

features-by-page

06

training-and-evaluation

Use when training Roboflow models or improving accuracy — covers architecture selection, model IDs, checkpoints, evaluation metrics, and the iterative improvement playbook.

improvement-playbook

07

universe

Use when searching for or using public datasets / models on Roboflow Universe (universe.roboflow.com) — the open repository of 1M+ computer vision datasets and 50K+ pre-trained models.

datasets

models

For AI agents

A short, LLM-friendly summary lives at /llms.txt

Quick answers about the server, Skills, auth, and how MCP fits into the rest of Roboflow.

curl

$

curl https://mcp.roboflow.com/llms.txt

#

Roboflow MCP Server

#

Endpoint: https://mcp.roboflow.com/mcp

#

Transport: streamable HTTP

#

Auth: x-api-key header

#

30 tools across 9 categories…

Ready to give your agent vision?

Get started View Docs

FAQ

Frequently asked questions.

Quick answers about the server, Skills, auth, and how MCP fits into the rest of Roboflow. Don't see yours? Check the docs.

What is the Roboflow MCP Server?

The Roboflow MCP Server is a hosted Model Context Protocol (MCP) server at mcp.roboflow.com that gives AI coding agents direct access to a Roboflow workspace. It exposes 30 tools across projects, datasets, training, Workflows, and Universe, so any MCP-compatible client (Claude, Claude Code, Cursor, Codex, Windsurf, Continue) can manage computer vision projects through natural-language prompts. The one-command installer wires up the server connection along with Skills, expert markdown playbooks the agent reads as MCP resources.

‍

What's the difference between MCP and Skills?

MCP gives your agent the tools (verbs). Skills give it the expert knowledge (when, why, and how). Tools are live primitives like 'create a project' or 'run a Workflow.' Skills are durable markdown playbooks: api-reference, data-management, inference, plans-and-pricing, product-navigation, training-and-evaluation, and universe.

How is this different from the Roboflow REST API?

The REST API is for code. MCP is for agents. The server speaks streamable HTTP at /mcp and presents 30 tools your AI agent can discover and call directly. It is tuned for natural language to tool call workflows rather than hand-written integrations.

Which agents are supported?

The plugin manifest ships for Claude Code and Codex. The Skills CLI installs standalone Skills into Claude Code, Cursor, OpenCode, and any agent that reads SKILL.md files. The MCP server itself works with anything that speaks MCP over streamable HTTP.

Do I need to install anything locally?

The MCP server is hosted at mcp.roboflow.com, so it runs in the cloud. The plugin install pulls the Skills bundle and writes the MCP config locally so your agent knows about the server. If you only want the live tools, paste the .mcp.json snippet from this page into your client config by hand instead.

How do I authenticate?

Set ROBOFLOW_API_KEY in the shell that launches your agent (run export ROBOFLOW_API_KEY=your_key, or add it to ~/.zshrc or a project .env). The plugin reads the value from your environment; direct MCP clients pass it in the x-api-key header. Grab a key from app.roboflow.com/settings/api.

Can I install per project?

Yes. claude plugin install roboflow --scope local writes the plugin into the current project only and reads the API key from that project environment. Useful when different projects need different ROBOFLOW_API_KEY values for different workspaces.

Is it free?

The MCP server, Skills, and plugin are free and open source under Apache-2.0. You only pay for the underlying Roboflow usage on the same plans you already have.

Where can I report a bug or suggest a Skill?

Open an issue or PR on roboflow/computer-vision-skills. Skills are markdown; contributions are mostly editing or adding files under skills/, each with a SKILL.md frontmatter block.