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 do I audit the parameters used in a specific experiment?

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

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

Absolutely. Use the 'list_experiments' tool 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.

Comet ML MCP Server for Claude Desktop 6 tools — connect in under 2 minutes

Name: Comet ML
Availability: InStock
Author: Vinkius

modelcontextprotocol.io/quickstart/user

Built by Vinkius GDPR 6 Tools IDE

Claude Desktop is Anthropic's native application for interacting with Claude AI models on macOS and Windows. It was the first consumer application to ship with built-in MCP support, making it the reference implementation for the Model Context Protocol standard.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

RecommendedModern Approach — Zero Configuration

Vinkius Desktop App

The modern way to manage MCP Servers — no config files, no terminal commands. Install Comet ML and 2,500+ MCP Servers from a single visual interface.

Download Free Open SourceNo signup required

Classic Setup·json

{
  "mcpServers": {
    "comet-ml": {
      // Your Vinkius token. get it at cloud.vinkius.com
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Comet ML MCP Server

Connect your Comet ML account to any AI agent and take full control of your machine learning lifecycle through natural conversation.

Claude Desktop is the definitive way to connect Comet ML to your AI workflow. Add Vinkius Edge URL to your config, restart the app, and Claude immediately exposes all 6 tools in the chat interface. ask a question, Claude calls the right tool, and you see the answer. Zero code, zero context switching.

What you can do

Experiment Tracking — List and audit machine learning runs to inspect performance metadata, tags, and live execution statuses
Numeric Metric Auditing — Retrieve high-precision numeric endpoints mapping metrics generated dynamically during your training loops
Parameter Inspection — Extract explicit ML properties like learning rates and configurations logged to specific experiment keys
Project & Workspace Navigation — Navigate through organizational namespaces and identify exactly where your ML research resides
Run Metadata Analysis — Discovered disconnected physical limits parsing explicit run structures, timing, and structural configurations

The Comet ML MCP Server exposes 6 tools through the Vinkius. Connect it to Claude Desktop in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Comet ML to Claude Desktop via MCP

Follow these steps to integrate the Comet ML MCP Server with Claude Desktop.

Open Claude Desktop Settings

Go to Settings → Developer → Edit Config to open claude_desktop_config.json

Add the MCP Server

Paste the configuration above into the mcpServers section

Restart Claude Desktop

Close and reopen Claude Desktop to load the new server

Start using Comet ML

Look for the 🔌 icon in the chat. your 6 tools are now available

Why Use Claude Desktop with the Comet ML MCP Server

Claude Desktop by Anthropic provides unique advantages when paired with Comet ML through the Model Context Protocol.

Claude Desktop is the reference MCP client. it was designed alongside the protocol itself, ensuring the most complete and stable MCP implementation available

Zero-code configuration: add a server URL to a JSON file and Claude instantly discovers and exposes all available tools in the chat interface

Claude's extended thinking capability lets it reason through multi-step tool usage, chaining multiple API calls to answer complex questions

Enterprise-grade security with local config storage. your tokens never leave your machine, and connections go directly to Vinkius Edge network

Comet ML + Claude Desktop Use Cases

Practical scenarios where Claude Desktop combined with the Comet ML MCP Server delivers measurable value.

Interactive data exploration: ask Claude to query DNS records, look up WHOIS data, and cross-reference results in a single conversation

Ad-hoc security audits: type a domain name and let Claude enumerate subdomains, check DNS history, and flag configuration anomalies. all through natural language

Executive briefings: generate comprehensive domain intelligence reports by asking Claude to compile findings into a formatted summary

Learning and training: new team members can explore API capabilities conversationally without needing to read documentation

Comet ML MCP Tools for Claude Desktop (6)

These 6 tools become available when you connect Comet ML to Claude Desktop via MCP:

get_experiment

Retrieve explicit Cloud logging tracing explicit Payload IDs

get_experiment_metrics

Execute static mapping targeting exactly defined numeric bounds natively

get_experiment_params

Inspect internal properties detailing API taxonomy types

list_experiments

Discover explicit routing arrays structuring specific logged experiment limits

list_projects

Perform structural extraction matching target Projects inside Comet

list_workspaces

Identify bounded routing spaces inside the Headless Comet ML limits

Example Prompts for Comet ML in Claude Desktop

Ready-to-use prompts you can give your Claude Desktop agent to start working with Comet ML immediately.

"List all projects in workspace 'research-team'"

"Get current metrics for experiment 'exp_abc123'"

"What hyperparameters were used in experiment 'exp_789'?"

Troubleshooting Comet ML MCP Server with Claude Desktop

Common issues when connecting Comet ML to Claude Desktop through the Vinkius, and how to resolve them.

Server not appearing after restart

Ensure the JSON is valid (no trailing commas). Check the file path: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\\Claude\\ (Windows).

Authentication error

Verify your Vinkius token is correct. Go to cloud.vinkius.com to regenerate it if needed.

Tools not showing in chat

Click the 🔌 icon at the bottom of the chat input. If it shows 0 tools, the server may still be connecting. wait a few seconds.

Comet ML + Claude Desktop FAQ

Common questions about integrating Comet ML MCP Server with Claude Desktop.

How does Claude Desktop discover MCP tools?

When Claude Desktop starts, it reads the claude_desktop_config.json file and connects to each configured MCP server. It calls the tools/list endpoint to fetch the schema for every available tool, then surfaces them as clickable options in the chat interface via the 🔌 icon.

What happens if the MCP server is temporarily unavailable?

Claude Desktop handles disconnections gracefully. if the server is unreachable at startup, the tools simply won't appear. Once the server becomes available again, restarting Claude Desktop will re-establish the connection. There is no timeout penalty or error loop.

Can I connect multiple MCP servers simultaneously?

Yes. You can add as many servers as you need in the mcpServers section of the config file. Each server appears as a separate tool provider, and Claude can use tools from multiple servers in a single conversation turn.

Is there a limit on the number of tools per server?

Claude Desktop can handle hundreds of tools per server. However, for optimal LLM performance, Vinkius servers are designed to expose focused, well-documented tool sets rather than overwhelming the model with too many options.

Does Claude Desktop support Streamable HTTP transport?

Yes. Claude Desktop supports both SSE (Server-Sent Events) and the newer Streamable HTTP transport that Vinkius uses. Simply provide the server URL. Claude auto-negotiates the transport protocol.