How to Use the Weights & Biases MCP in Vercel AI SDK

Q: How do I find all available projects in Weights & Biases using Vercel AI SDK?

You use the listwandbprojects tool. This function queries your entire W&B entity and returns a list of every project name or ID you have access to. You can then pass that list to guide subsequent user interactions.

Q: Can I list all experiment runs in a specific W&B project with Vercel AI SDK?

Yep. The listprojectruns tool lets you pull every single run ID from a specified W&B project. This gives the user an immediate, paginated overview of their entire experimental history.

Q: Does Weights & Biases support listing reports with Vercel AI SDK?

Yes, you use listprojectreports. It pulls a list of saved analysis report names from a W&B project. This is useful for showing users which analyses they've already generated.

See your W&B metrics stream directly into the React UI using Vercel AI 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 Vercel AI SDK

Create your Vinkius account to connect Weights & Biases to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Displaying Project Artifacts in Real Time

When a user asks for project assets, you can list all available artifacts (datasets or models) using `list_project_artifacts`. This shows the front end exactly what resources are stored under a given W&B project. You'll get immediate data feedback that streams into your component. The client calls this tool and sends the results straight to the user interface, avoiding any loading spinners.

Fetching Detailed Run Information

Need deep metrics on one specific experiment? Call `get_run_details` with a run ID. This pulls everything—summary metrics and config settings—into your streamable response. This lets you build a dynamic dashboard where the user sees the full performance profile update instantly as data streams into the page.

Tracking Hyperparameter Sweeps

The system can list all hyperparameter search sweeps using `list_project_sweeps`. This function returns a clean overview of how many attempts were made and what ranges were tested. Passing this data to the SDK means your UI displays sweep statistics live. It's perfect for showing users optimization progress as it happens.

Setup guide

Set up Weights & Biases MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Weights & Biases tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Weights & Biases transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You use the `list_wandb_projects` tool. This function queries your entire W&B entity and returns a list of every project name or ID you have access to. You can then pass that list to guide subsequent user interactions.

This server primarily handles structured metadata: project names, run IDs, artifact lists, and hyperparameter ranges. It focuses on reading configuration data rather than raw metric payloads.

Yep. The `list_project_runs` tool lets you pull every single run ID from a specified W&B project. This gives the user an immediate, paginated overview of their entire experimental history.

Yes, you use `list_project_reports`. It pulls a list of saved analysis report names from a W&B project. This is useful for showing users which analyses they've already generated.

The server touches metadata like project IDs and artifact names. Since this is configuration data, you're safe as long as your API key only has read access to the necessary W&B projects.

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