How to Use the Comet ML MCP in Claude Code

Connect Comet ML to Claude Code for headless experiment logging and metric extraction in your CLI.

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 Code

Create your Vinkius account to connect Comet ML to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Claude Code tracks Comet ML runs

Use `list_experiments` to pipe your run history into your terminal. Claude Code parses the routing arrays so you can filter results in your bash scripts. `list_projects` and `list_workspaces` help your CI/CD pipeline find the right target. It makes automated auditing a breeze.

Automate metric checks with Claude Code

Claude Code invokes `get_experiment_metrics` to grab raw values from your latest runs. You can set up scripts that fail if your model misses its performance bounds. `get_experiment` pulls full payloads. You can pipe this output to other CLI tools for quick analysis.

Check parameters via Claude Code

Run `get_experiment_params` from the command line to inspect your API taxonomy. It gives you a clear view of your configuration settings. This MCP server acts as a bridge for your terminal. Your agent can now manage your ML lifecycle without a browser.

Setup guide

Set up Comet ML MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see comet-ml-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Comet ML transactions." It will automatically discover and invoke the available Comet ML tools.

Terminal

claude mcp add --transport http comet-ml-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Comet ML MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "comet-ml-mcp": {
      "type": "url",
      "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 Code

Use the command line to add the server URL. Run the add command with the correct transport flags, and verify it with the list command.

Yes. Claude Code can execute the metrics tool and return the output directly to your terminal or into a log file.

It does. You can list projects and workspaces via the CLI, which is perfect for building automated deployment pipelines.

Vinkius uses a zero-trust architecture. Your data is handled through a single endpoint token, and no persistent state remains after your job finishes.

It touches your Comet ML experiment tracing data and numeric run metrics. This sensitive information is processed through an isolated 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