Roboflow MCP Server staging

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

Claude Connector Recommended

Add Roboflow as a connector in your Claude account. Once connected, it works everywhere — Claude.ai, Desktop, and Claude Code.

Claude Code (CLI)

If you prefer the terminal:

claude mcp add -s user roboflow \
  --transport http https://mcp.roboflow.one/mcp
Cursor

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

{
  "mcpServers": {
    "roboflow": {
      "type": "http",
      "url": "https://mcp.roboflow.one/mcp"
    }
  }
}
Codex

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

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

For AI agents

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