# GraphRAG

> Use this tool when you need to perform powerful document search and context expansion, combining semantic search and graph-based relationships to retrieve contextually aware information. GraphRAG enables hybrid retrieval by integrating document embeddings and graph database capabilities, solving problems in applications like technical documentation systems and knowledge bases. It accepts queries and database schema information as inputs, and outputs relevant documents and contextual information, making it ideal for use cases requiring both semantic relevance and structural context.

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

## Description

GraphRAG MCP provides a hybrid retrieval system that combines Neo4j graph database and Qdrant vector database capabilities for powerful document search and context expansion. Developed by Riley Lemm, this server implementation enables semantic search through document embeddings, graph-based context expansion following relationships, and hybrid search combining both approaches. The server exposes tools for querying documentation and resources for accessing database schema information, making it particularly valuable for applications requiring both semantic relevance and structural context in document retrieval, such as technical documentation systems, knowledge bases, or any application needing contextually aware information retrieval.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-02

## Source

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

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