How to Use the Comet ML MCP in Claude

Q: Can Claude Desktop list my active Comet ML projects?

Yes, it uses the listprojects tool to search your workspace. Claude Desktop then displays the matching structural project data in a clean list.

Pull Comet ML run metrics and audit workspace experiments directly inside Claude Desktop.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Comet ML MCP to Claude Desktop

Create your Vinkius account to connect Comet ML to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Comet ML with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inspect Comet ML parameters in Claude Desktop

The `get_experiment_params` tool pulls exact API taxonomy types directly into your Claude Desktop chat window. You don't have to keep a browser tab open to check how you configured a training run. Just ask Claude Desktop to inspect the run. It uses `get_experiment` to fetch the explicit payload ID details, giving you the exact configuration values instantly.

Track ML metrics during your chat sessions

The `get_experiment_metrics` tool retrieves numeric bounds natively to show you how your loss curves are shaping up. Claude Desktop reads these numbers to tell you if your model is overfitting. You can also call `list_experiments` to check routing arrays and compare multiple runs. Claude Desktop formats these limits side-by-side so you spot the best run immediately.

Navigate Comet workspaces with this MCP Server

The `list_workspaces` tool maps out your active headless spaces inside your Claude Desktop panel. You get a clear view of where your team stores different training runs. Combine that with `list_projects` to extract specific project structures. Claude Desktop lists every project in your workspace without making you run a single CLI command.

Setup guide

Set up Comet ML MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Comet ML MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Comet ML MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under comet-ml-mcp.

json

{
  "mcpServers": {
    "comet-ml-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Comet ML. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Comet ML now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Comet ML MCP in Claude Desktop

Ask Claude Desktop to fetch your run details. The server runs `get_experiment_metrics` behind the scenes to pull your numerical training limits directly into the chat.

Yes, it uses the `list_projects` tool to search your workspace. Claude Desktop then displays the matching structural project data in a clean list.

Claude Desktop lacks native access to your ML runs. This MCP Server exposes `get_experiment_params` so the app can read your API taxonomy types.

Tell Claude Desktop to fetch the run ID you want. It invokes `get_experiment` to retrieve the exact logged tracing data.

Your Comet ML workspace names, experiment parameters, and numerical metrics never touch third-party databases. The MCP server runs locally on your machine via Claude Desktop's stdio transport, meaning your proprietary model parameters stay strictly inside your local environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript