Integrate Comet ML with Claude, Cursor, Chatbots & AI Agents MCP Server

Q: Can my agent retrieve real-time metrics from an active ML run?

Yes. Use the 'getexperimentmetrics' tool with the experiment key. The agent will pull the latest numeric logged endpoints, allowing you to monitor loss, accuracy, and other custom metrics as they are generated.

Manage machine learning experiments via Comet — track model metrics, audit project workspaces, and inspect ML run parameters directly from any AI agent.

GDPR Free for Subscribers

Compatible with every major AI agent and IDE

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

get

Get experiment on Comet ML

Retrieve explicit Cloud logging tracing explicit Payload IDs

get

Get experiment metrics on Comet ML

Execute static mapping targeting exactly defined numeric bounds natively

get

Get experiment params on Comet ML

Inspect internal properties detailing API taxonomy types

list

List experiments on Comet ML

Discover explicit routing arrays structuring specific logged experiment limits

list

List projects on Comet ML

Perform structural extraction matching target Projects inside Comet

list

List workspaces on Comet ML

Identify bounded routing spaces inside the Headless Comet ML limits

Security & Code Integrity Audit

Every tool in the Comet ML MCP Server is continuously audited by the Vinkius Security Engine. We guarantee zero-trust payload isolation, strict data boundaries, and deterministic execution for enterprise-grade AI agents.

A+Score: 98.33

How Vinkius protects your data

Can I set different limits for each virtual assistant on my team?

Absolutely. You have full control in our command center. You can create an AI agent that only "reads" data so the support team can answer questions, and another superpowered agent that can "edit" and "create" information exclusively for your operations team. Each AI gets exactly the level of access you allow.

Is there a risk of the AI "going crazy" and deleting important company data?

No. With Vinkius, the AI operates on "rails". It can only make the exact moves you authorized in the tool's settings. It cannot invent routes, access other networks in your company, or decide to delete random files. If the action isn't in the approved catalog, the attempt is blocked instantly.

Can my agent retrieve real-time metrics from an active ML run?

Yes. Use the 'get_experiment_metrics' tool with the experiment key. The agent will pull the latest numeric logged endpoints, allowing you to monitor loss, accuracy, and other custom metrics as they are generated.

How does the AI access my passwords and credentials?

It simply doesn't. On Vinkius, your passwords, API keys, and login details are kept in a secure vault. The AI (like ChatGPT or Claude) merely "asks" Vinkius to perform the task. Vinkius opens the door, does the work, and hands the result back to the AI. Your credentials are never seen, read, or learned by the artificial intelligence.

Supported Use Cases for Comet ML

The Comet ML integration provides comprehensive execution endpoints, allowing AI models to orchestrate tasks reliably.

Optimizing mlops with Claude

Connect the Comet ML server to enable mlops workflows. The integration provides structured schemas for Claude to mutate ship it data.

The Future of experiment tracking

The Comet ML MCP translates LLM intent into specific experiment tracking actions. Agents like Cursor use this to interface securely with your ship it infrastructure.