# MCPunk

> Use this tool when you need to efficiently search and navigate your codebase to find specific code snippets or answers to programming questions. MCPunk solves the problem of tedious manual code searching by breaking files into logical chunks and leveraging LLM tools to find relevant code. It takes in natural language queries as input and outputs relevant code snippets or answers, making it ideal for use during coding, debugging, or knowledge sharing.

Canonical page: https://skillsregistry.net/skills/jurasofish-mcpunk  
JSON: https://api.skillsregistry.net/v1/skills/jurasofish-mcpunk

## Description

Chat with your codebase through intelligent code searching without embeddings by breaking files into logical chunks, giving the LLM tools to search these chunks, and letting it find specific code needed to answer your questions.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-05

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dj9kxuocc6)
- **Repository:** <https://github.com/jurasofish/mcpunk>

## 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": "jurasofish-mcpunk"
    }
  }
}
```

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