How to Use the Comet ML MCP in VS Code Copilot

Q: Can my team share Comet ML configs in VS Code Copilot?

Yes, you can save the MCP Server setup in .vscode/mcp.json and commit it to Git. Everyone on your team gets access to the experiment tools instantly.

Q: How do I get Comet ML run parameters in VS Code Copilot?

Ask the agent to check your hyperparameters. It uses getexperimentparams to extract the exact taxonomy types from your active run.

Q: Does VS Code Copilot support tracking Comet ML metrics?

Yes, it calls getexperimentmetrics to fetch your numeric bounds. The agent then displays your model's loss and accuracy values directly in the chat.

Q: How do I list my experiments inside the editor?

Ask the agent to show your recent runs. It executes listexperiments to parse the logged experiment limits and prints them in your terminal window.

Audit Comet ML workspaces and pull training metrics directly into your VS Code Copilot agent chat.

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 VS Code Copilot

Create your Vinkius account to connect Comet ML to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Comet workspaces across your team

The `list_workspaces` tool maps out your headless Comet ML routing spaces inside VS Code Copilot. This MCP Server helps your entire engineering team view active workspaces without sharing API tokens manually. With `list_projects`, the agent extracts target project structures directly into your workspace. This ensures everyone on your team commits code that targets the correct project folders.

Pull live run metrics into VS Code Copilot

The `get_experiment_metrics` tool retrieves defined numeric bounds to show your model's performance inside the chat. VS Code Copilot reads these metrics to help you write documentation for your best models. You can also use `list_experiments` to view routing arrays of logged runs. VS Code Copilot compares these limits to suggest which model weights you should deploy.

Inspect run parameters with this MCP Server

The `get_experiment_params` tool extracts API taxonomy types straight into your editor. You don't have to search through web dashboards to find which hyperparameters you used for a specific run. If a run behaves weirdly, VS Code Copilot calls `get_experiment` to retrieve the explicit cloud tracing payload. This lets you debug configuration drift directly in your codebase.

Setup guide

Set up Comet ML MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Comet ML MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Comet ML tools listed. Try asking: "List my recent Comet ML transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Yes, you can save the MCP Server setup in `.vscode/mcp.json` and commit it to Git. Everyone on your team gets access to the experiment tools instantly.

Ask the agent to check your hyperparameters. It uses `get_experiment_params` to extract the exact taxonomy types from your active run.

Yes, it calls `get_experiment_metrics` to fetch your numeric bounds. The agent then displays your model's loss and accuracy values directly in the chat.

Ask the agent to show your recent runs. It executes `list_experiments` to parse the logged experiment limits and prints them in your terminal window.

Yes, the MCP server handles your workspace names, project structures, and experiment params via local stdio channels. No training metrics or proprietary run parameters are sent to external middleman servers.

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