How to Use the Comet ML MCP in Mastra AI

Build resilient ML ops workflows in Mastra AI using direct tools for Comet ML experiment control.

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 Mastra AI

Create your Vinkius account to connect Comet ML to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Comet ML experiment branching

Use `list_experiments` to trigger logic based on specific run limits. Your Mastra agents decide the next step based on the routing arrays returned. If an experiment hits a threshold, the workflow branches automatically. You handle the failure or success states without writing custom glue code.

Parameter inspection for logic gates

Call `get_experiment_params` to pull API taxonomy types into your agent memory. You build conditional rules that depend on actual run properties. This creates a tight loop between your ML experiments and your automation logic. The agent knows exactly what the model state is before moving forward.

Reliable workflow integration

The MCP server allows Mastra to perform structural extractions of your projects. You query `list_projects` to define the scope of your agent's work. It supports retries on failed tool calls. If the connection to your ML logs drops, the agent waits and tries again.

Setup guide

Set up Comet ML MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Comet ML tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "comet-ml-mcp-client",
  servers: {
    "comet-ml-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Comet ML Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Comet ML tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Comet ML transactions"
);
console.log(result.text);

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 Mastra AI

Add the server to your agent configuration and spread the tools into the agent's definition. The workflow engine handles the execution flow.

You can enable requireToolApproval in your client settings. This forces a human check before the agent modifies or retrieves sensitive ML records.

The integration supports exponential backoff for network-bound tasks. This ensures your ML pipelines stay running even during intermittent connectivity.

You define the URL in the servers object within your client. The framework handles the connection automatically.

Your experiment metadata stays within the secure Vinkius sandbox. Access requires a scoped token that limits the agent to only the specific projects you define.

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