The Weights & Biases MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Weights & Biases account. It provides structured and secure access to your W&B projects, runs, sweeps, artifacts, reports, automations, integrations, teams, and organizations, so your agent can explore projects, review experiment runs, inspect sweeps and reports, check workflows, and understand account access on your behalf.
- Project and experiment review: Have your agent list visible projects and review runs by name, state, and creation time.
- Sweep and artifact discovery: Direct your agent to find hyperparameter sweeps and inspect the artifact types defined in a project.
- Report exploration: Let the agent list available W&B reports for a project so you can quickly find relevant experiment analysis.
- Automation and integration checks: Instruct your agent to review accessible automations, Slack connections, channels, and webhook integration names for an entity.
- Account and team context: Have your agent identify the authenticated user, default entity, teams, organization details, and team membership information.