How to Use the Weights & Biases MCP in VS Code Copilot

Q: How does Weights & Biases work with VS Code Copilot?

The MCP Server is configured via .vscode/mcp.json and runs through the Copilot Chat Agent mode. This means all team members use the same, standardized toolset directly within their IDE.

Q: Can I list my projects using Weights & Biases in VS Code Copilot?

Yes, the listwandbprojects tool lets the agent check your entire entity and generate a master list of all available projects for the team.

Q: Does MCP Server support Weights & Biases in VS Code Copilot for corporate teams?

Absolutely. Because the configuration lives in .vscode/mcp.json, it's team-wide and easily managed through Git, making rollouts simple and auditable.

Q: How do I list all available projects for Weights & Biases in VS Code Copilot?

Use the listwandbprojects tool. It gives a definitive overview of every project within your organizational account, ensuring everyone knows what exists.

Standardize ML tooling across teams with VS Code Copilot and MCP Server.

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 VS Code Copilot

Create your Vinkius account to connect Weights & Biases to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Access Run Details via MCP Server

The `get_run_details` tool pulls full details for a specific Weights & Biases run, including all summary metrics and the original config. This means every developer on your team gets consistent access to critical experiment information. The shared `.vscode/mcp.json` ensures that whether you're in Python or R, the agent has this context available immediately.

Audit Project Assets with MCP Server

When onboarding a new team member, they can use `list_project_artifacts` to get an immediate inventory of all project assets—models, datasets, and more. This builds consistency across the entire engineering group. The agent also uses `list_project_reports` so that any developer can pull up saved analysis reports without needing specific permissions.

Track Sweep Status in VS Code Copilot

The `list_project_sweeps` tool allows the whole team to see which hyperparameter searches are active or finished within a Weights & Biases project. This visibility is crucial for coordinating ML efforts. Furthermore, `list_project_runs` helps developers narrow down exactly which specific experiments need review.

Setup guide

Set up Weights & Biases MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Weights & Biases MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Weights & Biases tools listed. Try asking: "List my recent Weights & Biases transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

The MCP Server is configured via `.vscode/mcp.json` and runs through the Copilot Chat Agent mode. This means all team members use the same, standardized toolset directly within their IDE.

Yes, the `list_wandb_projects` tool lets the agent check your entire entity and generate a master list of all available projects for the team.

This server deals with ML metadata: project run metrics, configurations, and artifact IDs. The focus is on tracking experiment history and model versions, never raw user PII.

Absolutely. Because the configuration lives in `.vscode/mcp.json`, it's team-wide and easily managed through Git, making rollouts simple and auditable.

Use the `list_wandb_projects` tool. It gives a definitive overview of every project within your organizational account, ensuring everyone knows what exists.

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