An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Comet ML to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage your entire machine learning lifecycle through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Comet ML.

  1. 01

    List workspaces

    This capability identifies the specific routing spaces available within your Comet ML account.

  2. 02

    Get experiment params

    Use this to inspect the internal properties and API taxonomy types of an experiment.

  3. 03

    Get experiment

    This capability retrieves specific Cloud logging data and Payload IDs for a given experiment.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Comet ML.

  1. 04

    Get experiment metrics

    This capability executes static mapping to pull exact numeric bounds for your metrics.

  2. 05

    List experiments

    This capability discovers the arrays of logged experiments within your account.

  3. 06

    List projects

    Use this to perform structural extraction of specific projects inside Comet.

Real work

What teams actually run

01

Hyperparameter Verification

Ask your agent to confirm the exact batch size or learning rate used in a specific run.

02

Performance Comparison

Have your agent pull metrics from two different experiments to compare accuracy.

03

Project Organization

Use the agent to find which workspace or project contains a specific set of trials.

04

Real-time Monitoring

Check the live status and timing of an active training run via your chat interface.

Automate a task

Put Comet ML to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Comet ML works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Comet ML to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

910ms average. Fast in production.

Comet ML is checked daily against the live service.

Daily averagePeak 1108ms
Oct 3Today
Fastest day
711ms
Slowest day
1108ms
14-day trend
Slowing+8%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Comet ML, so you can see the experience inside your AI.

It does not authenticate your account with Comet ML. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Comet ML Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Comet ML capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "comet-ml-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_C2PxqYqwffQi3V41WE8jlPynFSP048sA8SVR1PFT/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Comet ML in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Comet ML owners hand off.

This MCP is built for professionals managing complex machine learning lifecycles.

  • 01

    Data Scientists

    They use the agent to compare model metrics across different experiments.

  • 02

    ML Engineers

    They verify training configurations and audit parameters using natural language.

  • 03

    MLOps Teams

    They monitor active model evaluations and check experiment completion statuses.

FAQ

Questions Comet ML owners ask.

  • 01

    How do I connect Comet ML to my AI client?

    Subscribe to the MCP on Vinkius and provide your Comet ML API Key. Once connected, you can use it immediately in Claude, Cursor, or Windsurf.

  • 02

    Which AI clients are compatible with this MCP?

    This MCP works with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Where do I find my Comet ML API Key?

    You can find your API key in your Comet ML Account Settings under the API Keys section.

  • 04

    Can I check real-time training status?

    Yes, the MCP allows you to inspect live execution statuses and timing for your ML runs.

  • 05

    Does this MCP work with my existing workspaces?

    Yes, you can use the list_workspaces capability to navigate through your existing organizational namespaces.

  • 06

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

    Yes. Use the 'get_experiment_metrics' capability 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.

  • 07

    How do I audit the parameters used in a specific experiment?

    Provide the experiment key to your agent. The 'get_experiment_params' capability extracts all logged ML properties, helping you verify hyperparameters like learning rates, batch sizes, and model architectures.

  • 08

    Can I see a list of all experiments within a specific project?

    Absolutely. Use the 'list_experiments' capability with the project ID. Your agent will surface all ML runs within that project, including their status and metadata, so you can quickly identify the results you need.

Explore

More in Ship It

Suggestions

Connect Comet ML to Claude, Cursor, ChatGPT & more