Weights & Biases
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/wandb/wandb-mcp-server
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Weights & Biases from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.