Weights & Biases

Integrates with Weights & Biases machine learning platform for querying Weave traces and evaluations, retrieving experiment data,

wandb 66
Claude CodeClaude DesktopGeneric
View source ↗

Weights & Biases' official MCP server provides AI agents with direct access to W&B's machine learning platform, enabling querying of Weave traces and evaluations, GraphQL-based experiment data retrieval, trace counting, report creation with visualizations, and access to wandbot support. Built with FastMCP and supporting both STDIO and HTTP transports, it features multi-tenant session management with API key isolation, comprehensive authentication middleware, and optional Weave tracing for observability of MCP operations. The implementation is particularly valuable for ML practitioners and teams who want to integrate W&B's experiment tracking, model evaluation, and collaboration features directly into AI-assisted workflows for model development, performance analysis, and automated reporting.

Source

Repository: https://github.com/wandb/wandb-mcp-server

Maintain Weights & Biases?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[Weights & Biases on getagentictools](https://getagentictools.com/mcp/wandb-wandb-mcp-server?ref=badge)