# @penqwin/mcp

> Use this tool when you need to optimize context token usage for LLM agents, providing token-efficient codebase skeletons and reducing token consumption by 80-95%. It takes in source files and outputs structural information, enabling more efficient processing. Ideal for use cases where large codebases need to be analyzed, such as code completion, code review, or programming assistance.

Canonical page: https://skillsregistry.net/skills/sarinmsari-penqwin-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sarinmsari-penqwin-mcp

## Description

An AST-based MCP server that provides token-efficient codebase skeletons to LLM agents, reducing context token usage by 80-95% by exposing structural information instead of full source files.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/qq6tq6adtp)
- **Repository:** <https://github.com/Penqwin/penqwin-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": "sarinmsari-penqwin-mcp"
    }
  }
}
```

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