Roboflow MCP Server

Connect your AI agent to Roboflow and turn it into a computer vision expert. Once connected, your agent gains Roboflow tools and skills — it can manage datasets, train models, run inference, build Workflows, and tap into expert knowledge about computer vision best practices. See the documentation for details.

Installation

You'll need a Roboflow API key. Get yours at https://app.roboflow.com/settings/api.

Claude Code

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"

Claude Desktop

In Claude Desktop: Your AvatarSettingsDeveloperEdit Config

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"
      ]
    }
  }
}

Codex

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"

Cursor

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"
      }
    }
  }
}

For AI agents

A short, LLM-friendly summary of this server lives at /llms.txt following the llms.txt convention.