How to Use the Weights & Biases MCP in OpenAI Agents SDK

Q: Can I monitor multiple projects with Weights & Biases using OpenAI Agents SDK?

Yeah, you can. The listwandbprojects tool lets your agent list all W&B entities under a user or team account first. You then feed that project name into other tools to focus the agent's efforts.

Q: Does the MCP Server support listing experiment runs with Weights & Biases using OpenAI Agents SDK?

Absolutely. You use listprojectruns to get a list of all experiments in a project. This gives your agent the run IDs it needs for subsequent, deeper calls like getting specific details.

Build production ML agents for Weights & Biases using OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Weights & Biases MCP to OpenAI Agents SDK

Create your Vinkius account to connect Weights & Biases 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 Weights & Biases with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Specific Experiment Runs

Using `get_run_details`, your agent pulls all the specific metrics and configs from a single W&B run. It gives you the full picture: what happened, why it happened, and how good the results were. This is crucial for production systems; don't guess about performance. You get precise summary data points that let your agents make informed decisions based on real experiment outcomes.

Discover Project Artifacts

The `list_project_artifacts` tool lets your agent see every piece of collateral saved in a project, like model checkpoints or datasets. It's a simple inventory check—you can tell your agents exactly what resources are available. Forget digging through folders manually. Your AI client pulls the names and types of artifacts right into the workflow, letting specialized agents hand off tasks using proven assets.

Analyze Hyperparameter Sweeps

If you're tuning models, `list_project_sweeps` shows your agent every hyperparameter search that has run in a project. It lists the parameters and boundaries you tested—the full scope of your optimization efforts. This means your deployed system knows exactly what combinations were tried before it settled on the best approach. You get visibility into the entire testing matrix.

Setup guide

Set up Weights & Biases 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 Weights & Biases tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Weights & Biases 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="Weights & Biases Agent",
            instructions="You have access to Weights & Biases 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 Weights & Biases. 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 Weights & Biases 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 Weights & Biases MCP in OpenAI Agents SDK

The MCP Server exposes W&B tools directly to your agent system, letting it read metrics and metadata. Your agent doesn't need specialized libraries; it just calls the exposed functions via the secure API endpoint.

Yeah, you can. The `list_wandb_projects` tool lets your agent list all W&B entities under a user or team account first. You then feed that project name into other tools to focus the agent's efforts.

You can access run details, artifact lists, report names, and sweep metadata. The server handles all of this structure so your agent gets clean, predictable JSON objects every time.

Absolutely. You use `list_project_runs` to get a list of all experiments in a project. This gives your agent the run IDs it needs for subsequent, deeper calls like getting specific details.

This MCP Server touches structured run metrics and configs. When configuring the agent, you'll be dealing with model performance data—things like loss curves, accuracy scores, and hyperparameter settings.

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