# mcp-wandb

> Use this tool when you need to integrate Large Language Models (LLMs) with Weights & Biases experiments, enabling agents to query and retrieve project details, run metrics, and plots. It solves problems related to experiment tracking, metrics analysis, and model performance evaluation. The tool accepts experiment-related queries as input and outputs relevant project and run data, making it useful for model training, evaluation, and optimization contexts.

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

## Description

Enables LLM agents to query Weights & Biases experiments, including listing projects, runs, metrics, plotting metrics, and retrieving run details.

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/tovixiecgt)
- **Repository:** <https://github.com/tsilva/mcp-wandb>

## 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": "tsilva-mcp-wandb"
    }
  }
}
```

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