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 OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: Comet ML
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Comet ML through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Comet ML Assistant",
            instructions=(
                "You help users interact with Comet ML. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Comet ML"
        )
        print(result.final_output)

asyncio.run(main())

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.

The OpenAI Agents SDK auto-discovers all 6 tools from Comet ML through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Comet ML, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

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 OpenAI Agents SDK 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 OpenAI Agents SDK via MCP

Follow these steps to integrate the Comet ML MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 6 tools from Comet ML

Why Use OpenAI Agents SDK with the Comet ML MCP Server

OpenAI Agents SDK provides unique advantages when paired with Comet ML through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Comet ML + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Comet ML MCP Server delivers measurable value.

Automated workflows: build agents that query Comet ML, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Comet ML, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Comet ML tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Comet ML to resolve tickets, look up records, and update statuses without human intervention

Comet ML MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect Comet ML to OpenAI Agents SDK 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 OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK 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 OpenAI Agents SDK

Common issues when connecting Comet ML to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Comet ML + OpenAI Agents SDK FAQ

Common questions about integrating Comet ML MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.