Weights & Biases Connector for AI agents.

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

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

Q: Is it possible to list versioned datasets and models?

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

Q: Can I monitor hyperparameter search sweeps via chat?

Yes. Use the listprojectsweeps tool 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.

6 live capabilities

Manage machine learning experiments and track model training metrics in real-time.

Live agent request Weights & Biases / Connector

Waiting for input…

AI Agent

Why people use Weights & Biases

Weights & Biases for Tracking ML Experiment Metrics

This Connector changes that by putting your Weights & Biases data right where you work. You can just ask your agent to pull the latest accuracy or check the config of a specific run. It turns your experiment history into a searchable knowledge base, letting you focus on the science instead of the navigation.

What Vinkius changes

You get a conversational interface for your entire machine learning experiment history.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

Real-world use case 01

The 'Where was that?' scenario

A researcher needs to find the specific hyperparameters used in a run from three weeks ago.
Real-world use case 02

The 'Did it crash?' check

An engineer wants to know if the current training job is still running or if it hit an error.
Real-world use case 03

The 'Data Audit'

A team needs to verify which model weights are associated with the latest production dataset.

Complete set · 6capabilities

The complete Weights & Biases capability set.

These are the exact actions your AI can choose when you ask it to work with Weights & Biases.

Capability set01 / 02

01—03

3 capabilities in this set.

Part of 6 available through Weights & Biases.

01 Capability
List project artifacts
Lists all datasets, models, and files stored within a specific project. Use this to audit your data lineage and file versions.
02 Capability
List wandb projects
Shows all projects under your user account or team entity. This makes it easy to navigate your different research areas.
03 Capability
List project runs
Lists every experiment run within a specific project. Use this to find the right run ID when you have dozens of experiments.

Capability set02 / 02

04—06

3 capabilities in this set.

Part of 6 available through Weights & Biases.

04 Capability
List project sweeps
Shows all hyperparameter search sweeps currently happening or finished in a project. It lets you monitor optimization progress.
05 Capability
Get run details
Pulls the full summary, including metrics and config, for a specific experiment run. This helps you see exact results without opening a browser.
06 Capability
List project reports
Displays all saved analysis reports and dashboards for a project. It helps you find collaborative documentation quickly.

Set up in minutes

One URL. Then ask Weights & Biases to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Weights & Biases from the conversation.

Choose your client

Live preview

Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp

Step 01

Open Connectors

In Claude Web or Claude Desktop, open Settings and choose Connectors.
Step 02

Add the URL

Choose Add custom connector, name it Weights & Biases, and paste the URL above.
Step 03

Turn it on in chat

Select +, open Connectors, and enable Weights & Biases for the conversation.

ChatGPT · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp

Step 01

Open MCP settings

On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
Step 02

Add the URL

Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Weights & Biases URL.
Step 03

Save and start

Save the connection and enable Weights & Biases in your conversation. Desktop may ask you to restart once.

Cursor · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "weights-biases": {
      "url": "https://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp"
    }
  }
}

Step 01

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
Step 02

Add the server config

Paste the JSON configuration above into the mcp.json file that opens
Step 03

Save the file

Cursor will automatically detect the new Connector
Step 04

Start using Weights & Biases

Open Agent mode in chat and ask: "Using Weights & Biases, help me...". 6 tools available

VS Code Copilot · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "weights-biases": {
      "url": "https://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp"
    }
  }
}

Step 01

Create MCP config

Create a .vscode/mcp.json file in your project root
Step 02

Add the server config

Paste the JSON configuration above
Step 03

Enable Agent mode

Open GitHub Copilot Chat and switch to Agent mode using the dropdown
Step 04

Start using Weights & Biases

Ask Copilot: "Using Weights & Biases, help me...". 6 tools available

Windsurf · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "weights-biases": {
      "url": "https://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp"
    }
  }
}

Step 01

Open MCP Settings

Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
Step 02

Add the server

Paste the JSON configuration above into mcp_config.json
Step 03

Save and reload

Windsurf will detect the new server automatically
Step 04

Start using Weights & Biases

Open Cascade and ask: "Using Weights & Biases, help me...". 6 tools available

Cline · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "weights-biases": {
      "url": "https://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp"
    }
  }
}

Step 01

Open Cline MCP Settings

Click the Connectors icon in the Cline sidebar panel
Step 02

Add remote server

Click "Add Connector" and paste the configuration above
Step 03

Enable the server

Toggle the server switch to ON
Step 04

Start using Weights & Biases

Ask Cline: "Using Weights & Biases, help me...". 6 tools available

Claude Code · Terminal command

Official guide ↗

Advanced setup

claude mcp add weights-biases --transport http "https://edge.vinkius.com/vk_preview_I1Yu40vJsqaxsdrmMLW0Zf84kGzji4jYFvnrqvBH/mcp"

Step 01

Install Claude Code

Run npm install -g @anthropic-ai/claude-code if not already installed
Step 02

Add the Connector

Run the command above in your terminal
Step 03

Verify the connection

Run claude mcp to list connected servers, or type /mcp inside a session
Step 04

Start using Weights & Biases

Ask Claude: "Using Weights & Biases, show me...". 6 tools are ready

Where the request belongs

Work Weights & Biases can move forward.

Built around the request

This is for the ML engineer who's tired of clicking through hundreds of nested folders in a dashboard at 2am, or the data scientist who needs to quickly verify which dataset version was used for a specific model.

ML Engineer

Checking if a training run crashed or if the loss curve looks normal during a late-night deployment.

Data Scientist

Verifying data lineage and finding the exact model weights used in a previous research paper.

Research Lead

Quickly summarizing the results of a multi-day hyperparameter sweep for the team.

AI Developer

Grabbing the latest metrics from a project to decide which model to move into production.

When one Connector is not enough

Combine Weights & Biases with the systems that finish the task.

View all recipes

Fine-Tune AI Models Using Connectors

GPT-4 costs $30 per 1M tokens for your classification task , fine-tune a $0.20/M model on Together AI that scores 96% accuracy, track every experiment in W&B, and save $29.80 per million tokens

Build the capability set

Each Connector adds new actions and data without changing how you work.

Browse Connectors

01 6 capabilities

DVC

Manage ML experiments via DVC. track projects and views, audit experiments history, and monitor model runs directly from any AI agent.

View Connector

02 6 capabilities

Comet ML

Manage machine learning experiments via Comet. track model metrics, audit project workspaces, and inspect ML run parameters directly from any AI agent.

View Connector

03 6 capabilities

Neptune.ai (ML Experiment Tracking)

Manage ML experiments via Neptune.ai. track training runs, monitor metrics, and audit model versions.

View Connector

04 6 capabilities

MLflow (ML Lifecycle Management)

Manage ML lifecycle via MLflow. track training runs, monitor metrics, and audit the model registry.

View Connector

05 6 capabilities

Arize AI

Monitor ML model performance, detect data drift, and troubleshoot prediction quality with real-time observability dashboards.

View Connector

06 6 capabilities

H2O.ai

Manage AI models via H2O.ai. track data frames, monitor machine learning models and training jobs, and audit cloud cluster status directly from any AI agent.

View Connector

Bring your own AI

Change the model, client or framework. Keep Weights & Biases connected.

Claude
ChatGPT
Gemini
Cursor
VS Code
Windsurf
ZCode
Cline
Zed
Continue
Kiro
Roo Code
Zencoder
Goose
Void
Augment Code
Amp
Qodo
Tabnine
Pieces
Sourcegraph Cody
JetBrains
Warp
Amazon Q
Antigravity
BoltAI
Raycast
Jan
LM Studio
AnythingLLM
Open WebUI
Msty
Cherry Studio
LibreChat
TypingMind
Chorus
5ire
n8n
LangChain
LlamaIndex
CrewAI
Vercel AI SDK

Before you connect

Questions about Weights & Biases.

The practical details behind the request, access and result.

Can I use the Weights & Biases MCP to see my training progress?

Yes, you can monitor live runs in real-time. Your agent can check the status of active jobs and report back on whether they are running, finished, or have crashed.

How do I access my team's projects with this Connector?

Once connected, your agent can list all projects within your team entity. You can then ask it to find specific project folders or reports shared by your colleagues.

Can this Connector help me find old model weights?

Yes, you can use it to list all artifacts within a project. This allows you to quickly identify specific model versions and their associated data lineage.

Does the Weights & Biases MCP support hyperparameter sweeps?

Yes, it can list all hyperparameter search sweeps. This makes it easy to see how your automated optimization jobs are progressing without manually checking the web dashboard.

How do I get my W&B data into my AI client?

You can connect the Weights & Biases MCP through the Vinkius catalog. Once linked, your AI client can access your experiment data using your W&B API key.

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.

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.

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.

One connection away

Give your agent a direct line to Weights & Biases.

Connect Weights & Biases once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available

Weights & Biases for Tracking ML Experiment Metrics

You get a conversational interface for your entire machine learning experiment history.

The 'Where was that?' scenario

The 'Did it crash?' check

The 'Data Audit'

List project artifacts

List wandb projects

List project runs

List project sweeps

Get run details

List project reports

Open Connectors

Add the URL

Turn it on in chat

Open MCP settings

Add the URL

Save and start

Open MCP Settings

Add the server config

Save the file

Start using Weights & Biases

Create MCP config

Add the server config

Enable Agent mode

Start using Weights & Biases

Open MCP Settings

Add the server

Save and reload

Start using Weights & Biases

Open Cline MCP Settings

Add remote server

Enable the server

Start using Weights & Biases

Install Claude Code

Add the Connector

Verify the connection

Start using Weights & Biases

ML Engineer

Data Scientist

Research Lead

AI Developer

Fine-Tune AI Models Using Connectors

DVC

Comet ML

Neptune.ai (ML Experiment Tracking)

MLflow (ML Lifecycle Management)

Arize AI

H2O.ai

Give your agent a direct line to Weights & Biases.