How to Use the Weights & Biases MCP in Windsurf

Q: Can I use Weights & Biases and Windsurf for model versioning?

Absolutely. To see what assets are available, Cascade runs listprojectartifacts. You'll get a full list of everything—datasets or models—stored in that specific project.

Q: Is Weights & Biases and Windsurf good for tracking all experiments?

It is. Running listprojectruns gives you an overview of every single experiment attempt. If you want the fine print, Cascade can then pull up the full metrics using getrundetails.

Automate your ML Ops workflow with Weights & Biases on Windsurf.

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 Windsurf

Create your Vinkius account to connect Weights & Biases to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze entire projects in one go.

Need to see what's happening across a whole project? Cascade starts by running `list_wandb_projects` to map out every entity you own. Then, it can dive into specific areas, using `list_project_runs` to pull together all the individual experiment attempts within that scope.

Check hyperparameter performance automatically.

Cascade figures out which model settings worked best by calling `list_project_sweeps`. If you want deeper metrics, it can then use `get_run_details` on a specific sweep result. You get the full summary and config without writing any multi-step prompts.

Manage model assets quickly.

Before deployment, you need to know what artifacts exist. Cascade calls `list_project_artifacts` for a quick inventory of datasets or models. If you also need the final analysis results, it can run `list_project_reports` to show all saved findings in that project.

Setup guide

Set up Weights & Biases MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Weights & Biases payment history." If connected, Cascade will call the Weights & Biases tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "weights-biases-mcp": {
      "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 Windsurf

Windsurf lets Cascade automatically generate a report workflow. You can set the goal to 'Compare best runs,' and it will autonomously execute `list_project_runs` first, then grab the needed details using `get_run_details`. It shows you the final output without needing multiple manual steps.

Yeah. You don't have to guess which projects exist. Cascade uses `list_wandb_projects` first, giving you a list of all projects under your user or team name right away. This makes starting any task fast.

Absolutely. To see what assets are available, Cascade runs `list_project_artifacts`. You'll get a full list of everything—datasets or models—stored in that specific project.

It is. Running `list_project_runs` gives you an overview of every single experiment attempt. If you want the fine print, Cascade can then pull up the full metrics using `get_run_details`.

This server touches project metadata, including run configuration details and summary metrics. When you connect it to your agent, the focus is on reading these structured ML experiment records.

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