# Weights & Biases

> Use this tool when you need to integrate machine learning experiment tracking, model evaluation, and collaboration into AI-assisted workflows. It solves problems of model development, performance analysis, and automated reporting by providing access to experiment data, visualizations, and wandbot support. The tool accepts API keys and query inputs, and outputs experiment data, reports, and visualizations through STDIO and HTTP transports.

Canonical page: https://skillsregistry.net/skills/wandb  
JSON: https://api.skillsregistry.net/v1/skills/wandb

## Description

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.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/wandb)
- **Repository:** <https://github.com/wandb/wandb-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "wandb"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wandb` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wandb/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt