GraphRAG FAQs

Question 1

What are the prerequisites for using GraphRAG?

Accepted Answer

You need Python 3.12+, a running Neo4j instance, a running Qdrant instance, and your document data indexed in both databases. See the documentation for detailed setup instructions.

Question 2

How does GraphRAG enhance document retrieval?

Accepted Answer

GraphRAG leverages semantic search using sentence embeddings and Qdrant, graph-based context expansion using Neo4j, and hybrid search combining both approaches for more accurate and context-aware results.

Question 3

What is the Model Context Protocol (MCP)?

Accepted Answer

The Model Context Protocol (MCP) is a standard that allows large language models (LLMs) to interact with external tools and resources. GraphRAG follows the MCP specification, enabling integration with MCP-enabled clients like Claude and Cursor.

Question 4

How do I integrate GraphRAG with Claude or Cursor?

Accepted Answer

Add the GraphRAG server to your MCP configuration file (e.g., `~/.cursor/mcp.json` for Cursor or Claude Desktop equivalent) and restart your MCP client.

Question 5

What is GraphRAG?

Accepted Answer

GraphRAG is a Model Context Protocol (MCP) server that combines Neo4j (graph database) and Qdrant (vector database) for enhanced document retrieval. It allows querying a hybrid graph and vector database system.

GraphRAG

GraphRAG

Key Features

Use Cases

Key Features

Use Cases