# Repository GraphRAG

> Use this tool when you need to build knowledge graphs of codebases and enable intelligent Q&A and change planning across multiple programming languages. It solves problems of code comprehension, refactoring guidance, and development planning by combining code parsing and document processing, and supports various inputs including directories and LLM providers. The tool provides outputs through three core interfaces: graph creation, query answering, and implementation planning.

Canonical page: https://skillsregistry.net/skills/yumeiriowl-repo-graphrag  
JSON: https://api.skillsregistry.net/v1/skills/yumeiriowl-repo-graphrag

## Description

GraphRAG-based MCP server that builds repository knowledge graphs by combining Tree-sitter code parsing with LightRAG document processing, enabling intelligent Q&A and change planning across codebases. Built by yumeiriowl, it supports 15+ programming languages (Python, Java, TypeScript, Rust, Go, etc.) and multiple LLM providers (OpenAI, Anthropic, Azure OpenAI, Gemini), using semantic similarity to merge code entities with document entities for unified understanding. The implementation provides three core tools: graph_create for building storage from directories, graph_query for answering questions about codebases, and graph_plan for generating implementation plans, making it valuable for code comprehension, refactoring guidance, and development planning across large repositories.

## Trust

- **Trust score (0–1):** 0.61
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/yumeiriowl-repo-graphrag)
- **Repository:** <https://github.com/yumeiriowl/repo-graphrag-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": "yumeiriowl-repo-graphrag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yumeiriowl-repo-graphrag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yumeiriowl-repo-graphrag/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