How to Use the Comet ML MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK guardrails block bad Comet ML runs?

Yes. You can configure your agent to read metrics via getexperimentmetrics and stop the pipeline if the numbers fail your validation checks.

Q: How does the OpenAI Agents SDK handle Comet ML workspace limits?

The agent uses listworkspaces to inspect your active limits. This keeps the agent from querying out-of-bounds workspaces that would throw API errors.

Get your OpenAI Agents SDK to pull Comet ML runs, track parameters, and verify model metrics with zero manual config.

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 OpenAI Agents SDK

Create your Vinkius account to connect Comet ML to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Comet ML metrics to OpenAI Agents SDK guardrails

Use `get_experiment_metrics` to grab raw run numbers and pass them directly to your OpenAI agent system. The agent checks those numeric bounds against your safety guardrails before triggering any deployment handoffs. If a training run drops below your accuracy threshold, the agent catches it. No silent failures. The metrics route directly through the OpenAI dashboard for clean tracing.

Discover workspaces natively with this MCP Server

This MCP Server exposes `list_workspaces` so your OpenAI agents can find where your models live without hardcoded paths. The agent queries your active workspaces and finds the right project structure on the fly. Once the workspace is found, the agent uses `list_projects` to map out the target directories. You don't have to write custom API wrappers for every new team workspace.

Trace experiment parameters during multi-agent handoffs

Call `get_experiment_params` to hand off tasks between specialized agents while keeping the context of your training runs intact. The first agent extracts the exact API taxonomy types and hands them to the deployment agent. The target agent uses those parameters to decide if a model is ready for production. All of these tool calls show up natively in your OpenAI tracing dashboard.

Setup guide

Set up Comet ML MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Comet ML tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Comet ML tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Comet ML tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Comet ML Agent",
            instructions="You have access to Comet ML tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Pass the server URL to MCPServerStreamableHttp and add it to your agent constructor. The SDK auto-discovers all six tools, including list_experiments, instantly.

Yes. You can configure your agent to read metrics via get_experiment_metrics and stop the pipeline if the numbers fail your validation checks.

The agent uses list_workspaces to inspect your active limits. This keeps the agent from querying out-of-bounds workspaces that would throw API errors.

Yes. Spin up the server using the Vinkius endpoint, then connect the SDK using the streamable HTTP transport.

Vinkius runs the server in an isolated sandbox. Your raw experiment parameters and workspace structures never pass through public logs.

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