apecloud/ApeRAGMCPMCP Server

ApeRAG

ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment

1.2kstars

132forks

Python

agentscontext-engineeringgraphragknowledge-graphmcp

Quality signals

ActiveNo testsNo CIThin docsNo licensePopular

Open Repository Download ZIP

AI summary

Auto-generated overview of what this skill does and when to reach for it.

Production-ready GraphRAG platform combining vector, graph, and full-text search with AI agents and MCP support for building knowledge-intensive AI applications.

Use this when

Need hybrid search across documents, graphs, and images
Want to deploy a scalable RAG system with Kubernetes
Building AI agents that autonomously search and reason over knowledge bases
Processing complex documents with tables, formulas, or visuals
Integrating AI assistants via Model Context Protocol (MCP)

Don't use when

Need a simple chatbot without knowledge graphs
Working with small datasets (<10k docs) where simpler RAG suffices
Requiring real-time responses with sub-second latency

Capabilities

Multi-modal indexing (text, graph, vision, tables)
Hybrid retrieval combining vector, full-text, graph, and summary search
Built-in AI agents with MCP tool support for autonomous reasoning
Kubernetes deployment with Helm charts for production
Advanced document parsing via MinerU for complex content
Graph-based entity normalization for cleaner knowledge graphs

InstallMCPRun via uvx (Python)

Universal installANY TOOL

$ npx skillcity@latest apecloud/ApeRAG

Auto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.

Requires Node.js 18+ (ships with npx).

Or install manually

uvx aperag

MCP Configuration

Add this to your claude_desktop_config.json

{
  "mcpServers": {
    "aperag": {
      "command": "uvx",
      "args": [
        "aperag"
      ]
    }
  }
}

Loading README…

Discover the toolingbehind modern intelligence

ApeRAG