How to Use the Weights & Biases MCP in Google ADK

Q: Can the Google ADK list all projects in Weights & Biases?

Yes, you use listwandbprojects to retrieve this master list. This allows your agent to scope its search across multiple W&B entities before diving into any single project.

Q: What specific tools are available in Weights & Biases using Google ADK?

The toolset includes getrundetails, listprojectartifacts, and many others. Your LlmAgent simply selects the right function name to execute the task.

Run enterprise ML agents on Weights & Biases using Google ADK.

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 Google ADK

Create your Vinkius account to connect Weights & Biases to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

List All W&B Projects

The `list_wandb_projects` tool lets your agent see every project name within a user or team account. This is your starting point for any large-scale, enterprise investigation. Your AI client can check the entire scope of work done in Weights & Biases by retrieving this master list, ensuring no critical initiative gets missed.

Retrieve Analysis Reports

By calling `list_project_reports`, your agent finds all saved analysis reports for a project. It doesn't just give you names; it confirms that the necessary documentation or analysis is ready to be acted upon. This helps your agent hand off tasks to another system, knowing exactly which completed report needs to be consumed by BigQuery or Vertex AI.

List All Experiment Runs

If you need an overview of every experiment, `list_project_runs` provides a comprehensive list within one project. It gives your agent the IDs needed for deeper context. This function acts as a quick table of contents, allowing your Google ADK-powered workflow to decide which specific runs require detailed checks or further data pulling.

Setup guide

Set up Weights & Biases MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Weights & Biases tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Weights & Biases_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Weights & Biases tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

The MCP Server exposes W&B tools as a callable toolset within your agent. Your Google ADK-powered workflow calls these functions, treating them like any native BigQuery or Vertex AI operation.

Yes, you use `list_wandb_projects` to retrieve this master list. This allows your agent to scope its search across multiple W&B entities before diving into any single project.

Since it's built on the Gemini ecosystem, it handles long context well. You can pass large amounts of aggregated W&B metadata (like full run lists) to your agent for complex reasoning.

The toolset includes `get_run_details`, `list_project_artifacts`, and many others. Your LlmAgent simply selects the right function name to execute the task.

The server touches structured run metrics and configs. When designing your enterprise agent, ensure that any sensitive model performance data pulled from W&B is handled according to BigQuery's security protocols.

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