# MCP TensorBoard

> Use this tool when you need to analyze and visualize machine learning experiment data, such as scalars, tensors, and images, to gain insights and optimize model performance. It solves problems related to ML experiment logging and visualization, providing a standardized API for querying and analyzing data. The tool accepts ML experiment logs as input and outputs visualized data and insights through the MCP API.

Canonical page: https://skillsregistry.net/skills/1kraks-mcp-tensorboard  
JSON: https://api.skillsregistry.net/v1/skills/1kraks-mcp-tensorboard

## Description

Exposes TensorBoard experiment data through a standardized MCP API, enabling AI coding agents to query and analyze scalars, tensors, histograms, distributions, and images from ML experiment logs.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/vkopbzwu3g)
- **Repository:** <https://github.com/1Kraks/mcp-tensorboard>

## 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": "1kraks-mcp-tensorboard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/1kraks-mcp-tensorboard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/1kraks-mcp-tensorboard/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