Weights & Biases MCP Server

The official implementation of the W&B Models and Weave MCP server.

Remote serverstreamable-httpPython

What is the Weights & Biases MCP server?

Connect Weights & Biases to Claude, Cursor or any other MCP client and it stops being a tab you switch to. The official implementation of the W&B Models and Weave MCP server. The weights & biases mcp server is what makes that connection.

What the server does

Query and analyze your Weights & Biases data using natural language through the Model Context Protocol.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Cursor — For manual or local installation, see Option 2 below.
  • VSCode — The VSCode tool exposed by this server
  • Codex — The Codex tool exposed by this server

Credentials and setup notes

Configuration is passed through the environment: WANDB_API_KEY, WANDB_BASE_URL, YOUR_API_KEY, YOUR_WANDB_API_KEY, YOUR_BASE_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Weights & Biases's toolset — Cursor, VSCode, Codex — is a fair guide to whether it matches your workflow. It is maintained by wandb; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
CursorFor manual or local installation, see [Option 2](#general-installation-guide) below. </details>
VSCodeThe VSCode tool exposed by this server.
CodexThe Codex tool exposed by this server.

How to install the Weights & Biases MCP server

```json
{
  "mcpServers": {
    "wandb": {
     "command": "/Users/niware_wb/.local/bin/uvx",
      "args": [
        "--from",
        "git+https://github.com/wandb/wandb-mcp-server",
        "wandb_mcp_server"
      ],
      "env": {
        "WANDB_API_KEY": "<your-api-key>"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
WANDB_API_KEYCredential the server authenticates with.Yes
WANDB_BASE_URLEndpoint or connection string the server talks to.Yes
YOUR_API_KEYCredential the server authenticates with.Yes
YOUR_WANDB_API_KEYCredential the server authenticates with.Yes
YOUR_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Weights & Biases to Cursor.
  • Use Weights & Biases to VSCode.
  • Use Weights & Biases to Codex.

Frequently asked questions

Get your API key from [wandb.ai/authorize](https://wandb.ai/authorize) and use the hosted server at `https://mcp.withwandb.com` with one-click installation in Cursor or a one-command setup in Claude Code, OpenAI Codex, or Gemini CLI.