# CodeGrok MCP

> Use this tool when you need to efficiently search and retrieve specific code snippets from large codebases using natural language queries. The CodeGrok MCP solves problems of manual code searching, enabling AI assistants to quickly find relevant code examples and integrate them into development workflows. It takes natural language inputs and returns relevant code snippets as output, ideal for use cases like automated coding, code review, and software development.

Canonical page: https://skillsregistry.net/skills/dondetir-codegrok-mcp  
JSON: https://api.skillsregistry.net/v1/skills/dondetir-codegrok-mcp

## Description

Enables semantic code search for AI assistants by indexing codebases with embeddings and Tree-sitter, returning relevant snippets via natural language queries.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/zgwv5z0iit)
- **Repository:** <https://github.com/dondetir/CodeGrok_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": "dondetir-codegrok-mcp"
    }
  }
}
```

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