Ultralytics Platform MCP — Claude Code MCP server guide
Connects Claude Code to Ultralytics Platform to manage datasets, train vision models, and fetch weights. Built for developers orchestrating ML runs from the chat.
claude mcp add --env ULTRALYTICS_API_KEY=<ULTRALYTICS_API_KEY> --env ULTRALYTICS_API_BASE=<ULTRALYTICS_API_BASE> --transport stdio ultralytics-platform-mcp -- npx -y ultralytics-mcpWhat Ultralytics Platform MCP does
This server exposes Ultralytics Platform controls to your MCP client. It enables creating private workspaces, transferring local video files as datasets, launching fine-tuning runs for models like yolo11n, and checking epoch metrics. You can also trigger predictions on remote image URLs or save resulting weight files directly to your machine.
Running the package demands Node.js 20 or newer alongside a valid ULTRALYTICS_API_KEY. Uploading training material from local video clips depends on system binaries: ffmpeg and ffprobe must exist in your PATH. Without these media tools, video dataset ingestion fails immediately.
Jobs on the platform incur immediate charges. The server protects against unintended spend by enforcing the confirm_cost: true flag on training and export tools. Retrying training on an existing model checkpoint also requires confirm_history_loss: true, preventing accidental loss of recorded epoch logs.
What it helps with
- manage Ultralytics projects and datasets directly from chat
- upload local video files into platform datasets
- start and monitor fine-tuning runs for vision models
- download trained model weights to the local file system
- test model predictions using remote image links
Example prompts for the agent
- Check my Ultralytics projects and tell me which datasets are ready for training.
- Create a new private project named
traffic-camsand upload./clips/junction.mp4as data. - Start a 50-epoch training run for
yolo11non thetraffic-camsdataset.
How to install Ultralytics Platform MCP
Platform CLI
claude mcp add --env ULTRALYTICS_API_KEY=<ULTRALYTICS_API_KEY> --env ULTRALYTICS_API_BASE=<ULTRALYTICS_API_BASE> --transport stdio ultralytics-platform-mcp -- npx -y ultralytics-mcpReplace <…> with your own values
Platform CLI
codex mcp add ultralytics-platform-mcp --env ULTRALYTICS_API_KEY=<ULTRALYTICS_API_KEY> --env ULTRALYTICS_API_BASE=<ULTRALYTICS_API_BASE> -- npx -y ultralytics-mcpReplace <…> with your own values
Config file
{
"mcpServers": {
"ultralytics-platform-mcp": {
"command": "npx",
"args": [
"-y",
"ultralytics-mcp"
],
"env": {
"ULTRALYTICS_API_KEY": "<ULTRALYTICS_API_KEY>",
"ULTRALYTICS_API_BASE": "<ULTRALYTICS_API_BASE>"
}
}
}
}Replace <…> with your own values
Config file
{
"servers": {
"ultralytics-platform-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ultralytics-mcp"
],
"env": {
"ULTRALYTICS_API_KEY": "<ULTRALYTICS_API_KEY>",
"ULTRALYTICS_API_BASE": "<ULTRALYTICS_API_BASE>"
}
}
}
}Replace <…> with your own values
Platform CLI
gemini mcp add -e ULTRALYTICS_API_KEY=<ULTRALYTICS_API_KEY> -e ULTRALYTICS_API_BASE=<ULTRALYTICS_API_BASE> ultralytics-platform-mcp npx -y ultralytics-mcpReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Ultralytics Platform MCP
How do I install Ultralytics Platform MCP in Claude Code?
Run claude mcp add ultralytics-mcp -e ULTRALYTICS_API_KEY=<ULTRALYTICS_API_KEY> -- npx -y ultralytics-mcp. Generate the key in your Ultralytics Platform settings under API Keys.
What does Ultralytics Platform MCP do?
It gives your AI agent tools to interact with Ultralytics Platform. You can trigger training jobs, inspect loss metrics, process image inputs, and manage remote datasets.
Why are ffmpeg and ffprobe required?
The server uses them to inspect and process video files before dataset transmission. If ffmpeg and ffprobe are missing from PATH, uploading video datasets will fail.
