# Pakunoda-MCP

> Use this tool when you need to inspect and optimize machine learning models, as it provides AI agents with access to project state, resources, and tools for evaluating candidates, scores, and hyperparameters. The Pakunoda-MCP server takes in project data and outputs actionable insights and prompts for further optimization. Ideal for use cases requiring automated hyperparameter tuning and model selection.

Canonical page: https://skillsregistry.net/skills/rikenbit-pakunoda-mcp  
JSON: https://api.skillsregistry.net/v1/skills/rikenbit-pakunoda-mcp

## Description

MCP server that exposes Pakunoda project state to AI agents, providing resources, tools, and prompts for inspecting candidates, scores, and triggering hyperparameter searches.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bjqkcmmjeu)
- **Repository:** <https://github.com/rikenbit/Pakunoda-MCP>

## 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": "rikenbit-pakunoda-mcp"
    }
  }
}
```

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