How to integrate Weights & Biases MCP with OpenAI Agents SDK

This guide walks you through connecting Weights & Biases to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Weights & Biases agent that can list your projects, review training runs, compare sweeps, browse reports, and inspect artifacts through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Weights & Biases account through Composio's Weights & Biases MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Weights & Biases logoWeights & Biases
Api Key

Weights & Biases is an MLOps platform for tracking experiments, models, sweeps, artifacts, and reports. It helps ML teams monitor runs, compare results, and manage model development in one place.

10 Tools

Introduction

This guide walks you through connecting Weights & Biases to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Weights & Biases agent that can list your projects, review training runs, compare sweeps, browse reports, and inspect artifacts through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Weights & Biases account through Composio's Weights & Biases MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Weights & Biases with

Claude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Weights & Biases
  • Configure an AI agent that can use Weights & Biases as a tool
  • Run a live chat session where you can ask the agent to perform Weights & Biases operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Weights & Biases MCP server, and what's possible with it?

The Weights & Biases MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Weights & Biases account. It provides structured and secure access to your W&B projects, runs, sweeps, artifacts, reports, automations, integrations, teams, and organizations, so your agent can explore projects, review experiment runs, inspect sweeps and reports, check workflows, and understand account access on your behalf.

  • Project and experiment review: Have your agent list visible projects and review runs by name, state, and creation time.
  • Sweep and artifact discovery: Direct your agent to find hyperparameter sweeps and inspect the artifact types defined in a project.
  • Report exploration: Let the agent list available W&B reports for a project so you can quickly find relevant experiment analysis.
  • Automation and integration checks: Instruct your agent to review accessible automations, Slack connections, channels, and webhook integration names for an entity.
  • Account and team context: Have your agent identify the authenticated user, default entity, teams, organization details, and team membership information.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Weights & Biases project
  • Some knowledge of Python or Typescript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Weights & Biases.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Weights & Biases
const session = await composio.create(userId as string, {
  toolkits: ['weights_and_biases'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only weights_and_biases.
  • The router checks the user's Weights & Biases connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Weights & Biases.
  • This approach keeps things lightweight and lets the agent request Weights & Biases tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Weights & Biases. Help users perform Weights & Biases operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Weights & Biases and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Weights & Biases operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Weights & Biases.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Weights & Biases and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['weights_and_biases'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Weights & Biases. Help users perform Weights & Biases operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Weights & Biases MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Weights & Biases.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

Every Weights & Biases action and event your agent gets out of the box.

Get Current Viewer

Return the authenticated W&B user, default entity, and team names for connection context.

Get Organization

Return a W&B organization's identifiers and organization entity by exact name.

Get Team

Return a W&B team's identity and bounded membership metadata by exact team entity name.

List Artifact Types

Return one page of artifact types defined in a W&B project.

List Automations

Return one page of W&B automations accessible under an entity.

List Integrations

List one page of Slack workspace/channel metadata and webhook integration names for a W&B entity.

List Projects

Return one page of W&B projects visible under an entity.

List Reports

Return one page of beta W&B reports for a project.

List Runs

List one page of runs with IDs, display names, states, and creation times.

List Sweeps

Return one page of hyperparameter sweeps from a W&B project when sweeps are enabled for the account.

FRAMEWORKS

How to build Weights & Biases MCP Agent with another framework

Claude Agent SDK logo

Claude Agent SDK

Use Weights & Biases MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Weights & Biases MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Weights & Biases MCP with Claude Cowork

Codex logo

Codex

Use Weights & Biases MCP with Codex

OpenClaw logo

OpenClaw

Use Weights & Biases MCP with OpenClaw

Hermes logo

Hermes

Use Weights & Biases MCP with Hermes

CLI logo

CLI

Use Weights & Biases MCP with CLI

Google ADK logo

Google ADK

Use Weights & Biases MCP with Google ADK

LangChain logo

LangChain

Use Weights & Biases MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Weights & Biases MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Weights & Biases MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Weights & Biases MCP with LlamaIndex

CrewAI logo

CrewAI

Use Weights & Biases MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Weights & Biases MCP server, the agents and LLMs can only access a fixed set of Weights & Biases tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Weights & Biases and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Weights & Biases tools.

Yes, absolutely. You can configure which Weights & Biases scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Weights & Biases data and credentials are handled as safely as possible.

Start with Weights & Biases.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Weights & Biases tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies