csp-rag-mcp

youngs75/csp-rag-mcp

★ 0 stars Python 🤖 AI/LLM Updated 1d ago

RAG MCP server — PDF ingestion (Docling/Claude vision) + Milvus hybrid search + pluggable embeddings (Cohere/BGE-M3) over the Model Context Protocol

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "csp-rag-mcp": {
      "command": "uvx",
      "args": [
        "csp-rag-mcp"
      ]
    }
  }
}

Or install with pip: pip install csp-rag-mcp

README Excerpt

> RAG as an MCP server — PDF ingestion + Milvus hybrid search + pluggable embeddings, exposed over the [Model Context Protocol](https://modelcontextprotocol.io/). A reusable retrieval backend extracted from a customer-support-portal chatbot PoC. Drop it into Claude Desktop, Claude Code, or any MCP host and let the LLM `search`, `upsert`, and `ingest_pdf` directly.

Tools (7)

allbgedelete_docdoclingingest_pdfsearchupsert_chunks

csp-rag-mcp

Quick Install

README Excerpt

Tools (7)

Related AI/LLM Servers