How to Use the Weights & Biases MCP in Cursor

Q: Can I use Weights & Biases in Cursor to check project status?

Absolutely. Calling listwandbprojects is a quick way for the AI to map out your entire Weights & Biases entity, ensuring all relevant projects are available for the current task.

Q: How do I list all available projects for Weights & Biases in Cursor?

You'll use the listwandbprojects tool. The AI can then incorporate that comprehensive list into your code, perhaps as a source variable or validation check.

Q: Does MCP Server support Weights & Biases in Cursor for local development?

Yes, you configure the server connection via .cursor/mcp.json. This lets the agent access the Weights & Biases tools within your local project scope.

Write ML code that talks to Weights & Biases using Cursor.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inject Live Run Data into Code

The `get_run_details` tool allows the AI agent to pull live metrics and configuration data from a specific Weights & Biases run. The unique part is that this response gets injected directly into the code you're writing. You don't get mock data or stubs; the generated function calls use real API responses, making your code immediately actionable.

Discover Project Structure in Cursor

Need to reference a specific dataset or model? Use `list_project_artifacts` to pull that context. The agent then uses this live list when writing the surrounding boilerplate code. If you're debugging, running `list_project_runs` gives the current project scope so the AI knows exactly which experiments it should reference.

Manage Hyperparameters via Cursor

The `list_project_sweeps` tool lets your agent retrieve all the hyperparameter searches done in a Weights & Biases project. This context is critical when you're writing logic that needs to account for sweep boundaries. Pairing this with `list_project_reports` lets the AI write code that consumes specific analysis findings from those reports.

Setup guide

Set up Weights & Biases MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Weights & Biases MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Weights & Biases transactions." If the MCP tools are loaded correctly, Cursor will call the Weights & Biases tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.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 Cursor

Cursor's Agent mode calls the MCP tools. Instead of just giving you a text summary, it feeds the resulting JSON data directly into your code buffer, letting you write against live API responses.

Absolutely. Calling `list_wandb_projects` is a quick way for the AI to map out your entire Weights & Biases entity, ensuring all relevant projects are available for the current task.

This MCP Server handles ML metadata like run metrics and artifact identifiers. The focus is on experiment tracking details, not raw user inputs or sensitive personal identifying information (PII).

You'll use the `list_wandb_projects` tool. The AI can then incorporate that comprehensive list into your code, perhaps as a source variable or validation check.

Yes, you configure the server connection via `.cursor/mcp.json`. This lets the agent access the Weights & Biases tools within your local project scope.

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