MCP-RAGAnything Multi-modal RAG service exposing a REST API and MCP server for document indexing and knowledge-base querying, powered by RAGAnything and LightRAG. Two retrieval pathways are available: a graph-based LightRAG pipeline and a classical RAG pipeline using multi-query generation with LLM-as-judge scoring. Files are retrieved from MinIO object storage and indexed into a PostgreSQL-backed knowledge graph. Each project is isolated via its own . Architecture Clients (REST / MCP / Claude) | +++ +++ | +++ Application Layer MCP Servers (FastMCP) ++ | +++ +--++ +--++ +--++ /classi
| Stars | 12 |
| Forks | 2 |
| Language | Python |
| Category | MCP 服务器 |
| Quality Score | 36.2/100 |
| Open Issues | 1 |
| Last Updated | 2026-04-01 |
| Created | 2025-12-08 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~89k |
These tools work well together with mcp-raganything for enhanced workflows:
Explore other popular mcp 服务器 tools:
mcp-raganything is API/MCP wrapper for RagAnything. It is categorized as a MCP 服务器 with 12 GitHub stars.
mcp-raganything is primarily written in Python. It covers topics such as agents, ai, docling.
You can find installation instructions and usage details in the mcp-raganything GitHub repository at github.com/Kaiohz/mcp-raganything. The project has 12 stars and 2 forks, indicating an active community.