How to Use the Weights & Biases MCP in Claude Code

Q: How do I use Weights & Biases and Claude Code together?

You write a shell script that first calls listwandbprojects to get the scope. Then, you pipe that list into another command that uses the W&B API tools like listprojectruns. It's pure automation.

Q: Can I use Weights & Biases and Claude Code for auditing artifacts?

Yes. You can script an audit job that calls listprojectartifacts across multiple projects, ensuring all required models or datasets are present before deployment starts.

Q: Is Weights & Biases and Claude Code good for tracking sweeps in CI/CD?

It is. You can script a job that calls listprojectsweeps to check hyperparameter performance every night. The output streams directly into your pipeline logs, flagging any suboptimal runs.

Q: Does Weights & Biases and Claude Code handle project discovery?

Absolutely. A simple script running listwandbprojects confirms all active projects for a given user or team, which is essential when building multi-stage release pipelines.

Automate W&B reporting pipelines from the terminal with Claude Code.

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 Claude Code

Create your Vinkius account to connect Weights & Biases to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

List and audit all projects via script.

Need a cron job to check project health? You run `list_wandb_projects` directly in your shell script. This confirms which entities need monitoring across the whole organization.

Generate reports for CI/CD pipelines.

Setting up a GitHub Action is easy. A simple command running `list_project_reports` pulls all saved analysis results into your pipeline output, letting you check for compliance or status checks automatically.

Programmatic access to run details.

You can build a script that iterates through runs using `list_project_runs`. Then, piping the ID into another tool allows you to pull granular data with `get_run_details` for status checks.

Setup guide

Set up Weights & Biases MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see weights-biases-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Weights & Biases transactions." It will automatically discover and invoke the available Weights & Biases tools.

Terminal

claude mcp add --transport http weights-biases-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Weights & Biases MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "weights-biases-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

You write a shell script that first calls `list_wandb_projects` to get the scope. Then, you pipe that list into another command that uses the W&B API tools like `list_project_runs`. It's pure automation.

Yes. You can script an audit job that calls `list_project_artifacts` across multiple projects, ensuring all required models or datasets are present before deployment starts.

It is. You can script a job that calls `list_project_sweeps` to check hyperparameter performance every night. The output streams directly into your pipeline logs, flagging any suboptimal runs.

Absolutely. A simple script running `list_wandb_projects` confirms all active projects for a given user or team, which is essential when building multi-stage release pipelines.

This server touches project metadata. Specifically, it handles summary metrics and run configuration details that are exposed through the `get_run_details` tool when running a script.

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