# ChunkHound

> Use this tool when you need to research and understand complex codebases across multiple programming languages. ChunkHound solves problems of code discovery, architectural pattern extraction, and knowledge retrieval through semantic search and structural parsing. It takes in codebases as input and outputs institutional knowledge and architectural patterns through an MCP-compatible interface.

Canonical page: https://skillsregistry.net/skills/ofriw-chunkhound  
JSON: https://api.skillsregistry.net/v1/skills/ofriw-chunkhound

## Description

A local-first codebase intelligence tool that enables AI assistants to research codebases using semantic search, multi-hop relationship discovery, and structural parsing. It allows users to extract architectural patterns and institutional knowledge across 30+ programming languages through an MCP-compatible interface.

## 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:** search
- **Updated:** 2026-06-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x08qb8ypxj)
- **Repository:** <https://github.com/chunkhound/chunkhound>

## 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": "ofriw-chunkhound"
    }
  }
}
```

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