MCP For Claude Marketplace
Weights & Biases

Weights & Biases MCP Connector for Claude

A+

Track experiments, monitor ML runs, and manage artifacts on WandB — the developer platform for AI.

6 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Weights & Biases (WandB) account to any AI agent and manage your machine learning experiments through natural conversation.

What you can do

  • Project Management — List all projects within your WandB entity (user or team) to browse your experiment folders
  • Run Monitoring — List and track individual experiment runs within a project to monitor real-time activity
  • Deep Run Analysis — Retrieve full details for any run, including latest accuracies, losses, and hyperparameters
  • Artifact Management — List versioned datasets, models, and other artifacts to track data lineage and dependencies
  • Sweep Tracking — Monitor automated hyperparameter search sweeps to see optimization progress
  • Reports & Collaboration — List saved analysis reports and dashboards to access collaborative documentation

How it works

  1. Subscribe to this server
  2. Enter your WandB API Key and optional Base URL
  3. Start managing your ML experiments through Claude, Cursor, or any MCP-compatible client

No more manual browsing through complex experiment dashboards to check model performance. Your AI agent becomes your ML research assistant.

Who is this for?

  • Machine Learning Engineers — monitor model training progress and compare hyperparameters across multiple runs
  • Data Scientists — track data lineage and manage versioned artifacts for reproducible research
  • Research Teams — collaborate on experiment reports and monitor shared project sweeps through chat
  • AI Developers — quickly surface model metrics and experiment summaries for faster development cycles
machine-learningexperiment-trackingmlopsmodel-versioningdata-artifactsmodel-monitoring

6 tools expose this connector's capabilities to your AI agent.

get_run_details

Retrieves full details for a specific W&B run, including summary metrics and config

list_project_artifacts

Lists all artifacts (datasets, models, etc.) in a project

list_wandb_projects

Lists all projects within a Weights & Biases entity (user or team)

list_project_reports

Lists all saved analysis reports in a project

list_project_runs

Lists all experiment runs within a specific W&B project

list_project_sweeps

Lists hyperparameter search sweeps within a project

See how to talk to your AI agent using Weights & Biases.

List all runs in my 'transformer-nmt' project for entity 'ai-team'.

I found 5 runs in 'transformer-nmt': 'vibrant-sweep-1' (Running), 'crispy-forest-12' (Finished), 'solar-wind-15' (Crashed), and 2 others. Would you like the detailed summary for any of these?

Get the final accuracy and config for run ID 'vibrant-sweep-1'.

Run 'vibrant-sweep-1' summary: accuracy = 0.942, loss = 0.156. Config: learning_rate = 0.001, batch_size = 32, optimizer = 'adam'. It finished 2 hours ago after 50 epochs.

What artifacts are available in the 'resnet-training' project?

In project 'resnet-training', I found: 1. 'imagenet-subset' (Dataset, v3), 2. 'resnet50-weights' (Model, v5), and 3. 'training-logs' (Artifact, v1). Would you like to see the versions or metadata for these?

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

Related Connectors

AU

Authing MCP

10 tools Official

Cloud-native identity and access management platform — manage users, roles, and security logs via AI.

A+ View details →
SH

ShadowBot MCP

10 tools Official

Orchestrate ShadowBot RPA — manage automation robots, handle execution tasks, and monitor bot performance directly from any AI agent.

A+ View details →
CS

College Scorecard API MCP

6 tools Official

Access US college data — audit school performance and costs via AI.

A+ View details →
CP

CDC Public Health / 美国疾控中心 MCP

8 tools Official

U.S. CDC official health resources — search media, audit topics, and get health recommendations via AI.

A+ View details →