# mcp-codesearch

> mcp-codesearch — michaelkrauty-mcp-codesearch. Use this tool when you need to efficiently search and retrieve specific code snippets across multiple programming languages. It solves problems of code discovery, reuse, and maintenance by providing semantic search capabilities, supporting over 160 languages through AST-aware chunking and hybrid dense+sparse search. Ideal for use in development environments, such as git, where quick code reference and reuse are crucial.

Canonical page: https://skillsregistry.net/skills/michaelkrauty-mcp-codesearch  
JSON: https://api.skillsregistry.net/v1/skills/michaelkrauty-mcp-codesearch

## Description

MCP server for semantic code search — AST-aware chunking, hybrid dense+sparse search, 160+ languages

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** search
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/michaelkrauty/mcp-codesearch)

## 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": "michaelkrauty-mcp-codesearch"
    }
  }
}
```

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