Weights & Biases MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Weights & Biases MCP or direct API to inspect projects, summarize runs, compare sweeps, and review artifacts and reports through natural language.

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

Try Weights & Biases now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Weights & Biases
Try asking
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.

SETUP GUIDE

Connect Weights & Biases MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/openai @ai-sdk/mcp
Install the Composio SDK for Python or TypeScript
2

Initialize Client and Create Tool Router Session

typescript
import { Composio } from '@composio/core';

const composio = new Composio({ apiKey: 'your-api-key' });
const session = await composio.create('your-user-id');
console.log(`Tool Router session created: ${session.mcp.url}`);
Import and initialize the Composio client, then create a Tool Router session for Weights & Biases
3

Connect to AI Agent

typescript
import { openai } from '@ai-sdk/openai';
import { experimental_createMCPClient as createMCPClient } from '@ai-sdk/mcp';
import { generateText } from 'ai';

const client = await createMCPClient({
  transport: {
    type: 'http',
    url: session.mcp.url,
    headers: {
      'x-api-key': 'your-composio-api-key',
    },
  },
});

const tools = await client.tools();
const { text } = await generateText({
  model: openai('gpt-4o'),
  tools,
  messages: [{
    role: 'user',
    content: 'Compare sweep results in my Weights & Biases project and identify the best run'
  }],
  maxSteps: 5,
});

console.log(`Agent: ${text}`);
Use the MCP server with your AI agent (Anthropic Claude or Mastra)
SETUP GUIDE

Connect Weights & Biases API Tool with your Agent

1

Install Composio

typescript
npm install @composio/openai
Install the Composio SDK
2

Initialize Composio and Create Tool Router Session

typescript
import OpenAI from 'openai';
import { Composio } from '@composio/core';
import { OpenAIResponsesProvider } from '@composio/openai';

const composio = new Composio({
  provider: new OpenAIResponsesProvider(),
});
const openai = new OpenAI({});
const session = await composio.create('your-user-id');
Import and initialize Composio client, then create a Tool Router session
3

Execute Weights & Biases Tools via Tool Router with Your Agent

typescript
const tools = session.tools;
const response = await openai.responses.create({
  model: 'gpt-4.1',
  tools: tools,
  input: [{
    role: 'user',
    content: 'List recent runs for my Weights & Biases project and summarize failed runs'
  }],
});
const result = await composio.provider.handleToolCalls(
  'your-user-id',
  response.output
);
console.log(result);
Get tools from Tool Router session and execute Weights & Biases actions with your Agent

Why Use Composio?

AI Native Weights & Biases Integration

  • Supports both Weights & Biases MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable W&B Cloud GraphQL queries
  • Rich coverage for reading projects, runs, sweeps, artifact types, reports, teams, and organizations

Managed Auth

  • Secure API key handling so your agent never needs hard-coded Weights & Biases credentials
  • Central place to manage, scope, and revoke W&B access for each user
  • Per user and per environment credentials for safer experiment and model tracking workflows

Agent Optimized Design

  • Tools are tuned for language models, so agents can query W&B runs and projects with fewer mistakes
  • Clear tool schemas help agents fetch the right experiment data instead of guessing GraphQL shapes
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Weights & Biases
  • Scoped, least privilege access to W&B resources like teams, orgs, projects, and reports
  • Full audit trail of agent actions to support model governance, review, and compliance
FAQ

Frequently asked questions

Yes, Weights & Biases requires you to configure your own API key credentials. Once set up, Composio handles secure credential storage and API request handling for you.

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. Learn more.

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

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