An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Weights & Biases to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage your machine learning experiments through chat.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Weights & Biases.

  1. 01

    List project artifacts

    This capability pulls a list of all datasets, models, and other versioned files stored within a specific project.

  2. 02

    List wandb projects

    This capability retrieves all project folders belonging to your specific WandB user or team entity.

  3. 03

    List project sweeps

    This capability shows all active or completed hyperparameter optimization sweeps inside a project.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Weights & Biases.

  1. 04

    Get run details

    This capability fetches the full configuration and summary metrics, like accuracy and loss, for a specific run.

  2. 05

    List project reports

    This capability finds all saved analysis reports and collaborative dashboards associated with a project.

  3. 06

    List project runs

    This capability returns a list of all individual experiment runs within a chosen project.

Real work

What teams actually run

01

Hyperparameter Optimization

Ask your agent to check the progress of a sweep to see if the optimization is converging.

02

Model Versioning

Quickly find the specific model weights or dataset version used in a successful run.

03

Performance Audits

Request a summary of accuracy and loss for a specific run to verify model quality.

04

Project Organization

Use the agent to list all projects and reports within your team entity.

Automate a task

Put Weights & Biases to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Weights & Biases works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Weights & Biases to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

903ms average. Fast in production.

Weights & Biases is checked daily against the live service.

Daily averagePeak 1121ms
Oct 3Today
Fastest day
709ms
Slowest day
1121ms
14-day trend
Stable-4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Weights & Biases, so you can see the experience inside your AI.

It does not authenticate your account with Weights & Biases. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Weights & Biases Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Weights & Biases capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "weights-biases-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Weights & Biases in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Weights & Biases owners hand off.

This is built for technical teams managing large-scale machine learning workflows.

  • 01

    Machine Learning Engineers

    They use the agent to monitor training progress and compare hyperparameters across runs.

  • 02

    Data Scientists

    They use the agent to track data lineage and manage versioned artifacts.

  • 03

    Research Teams

    They use the agent to access collaborative reports and monitor shared project sweeps.

FAQ

Questions Weights & Biases owners ask.

  • 01

    How do I connect my Weights & Biases account?

    You subscribe to the MCP on Vinkius and enter your WandB API Key. Once connected, your AI client can immediately access your data.

  • 02

    Which AI clients can I use with this MCP?

    You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I see my hyperparameter sweeps?

    Yes, the MCP includes a capability to list all hyperparameter search sweeps within a project.

  • 04

    Does this work with team accounts?

    Yes, you can list projects and runs for any WandB entity, whether it is a personal user or a team.

  • 05

    Can I retrieve specific model weights?

    The MCP allows you to list and identify versioned artifacts, including models and datasets, within your projects.

  • 06

    Can I check the latest metrics for a specific ML run?

    Yes. Using the get_run_details capability, your AI agent can pull the latest logged metrics (like accuracy or loss) and hyperparameters for any specific run ID within your projects.

  • 07

    Is it possible to list versioned datasets and models?

    Absolutely. The list_project_artifacts capability allows you to see all artifacts, including datasets and models, helping you track data lineage and versioning directly through conversation.

  • 08

    Can I monitor hyperparameter search sweeps via chat?

    Yes. Use the list_project_sweeps capability to monitor automated optimization tasks. Your agent will return a list of sweeps in the project so you can track progress without leaving your workspace.

Explore

More in AI Frontier

Suggestions

Connect Weights & Biases to Claude, Cursor, ChatGPT & more