andyliszewski/grounding-ai
Build a searchable index from PDFs, EPUBs, and Word docs. Claude queries it via MCP and pulls grounded answers with exact page-and-section citations. Local-first, no cloud dependency.
Ads
Overview
Grounding converts PDF, EPUB, DOCX, and Markdown documents into a structured, searchable corpus with per-agent embedding indexes. Drop documents into staging, get chunked Markdown with provenance hashing, FAISS vector indexes, and agent-filtered search -- all running locally, no cloud APIs required.
Installation
pip install grounding-ai
Configuration
{
"mcpServers": {
"grounding-ai": {
"command": "uvx",
"args": [
"grounding-ai"
]
}
}
}Paste into ~/.cursor/mcp.json or .cursor/mcp.json
Tags
- awesome-list
Related MCP servers
end to end RAG platforms
poll-the-people/customgpt-mcp
An MCP server for accessing all of CustomGPT.ai's anti-hallucination RAG-as-a-service API endpoints.
end to end RAG platforms
vectara/vectara-mcp
An MCP server for accessing Vectara's trusted RAG-as-a-service platform.
end to end RAG platforms
gogabrielordonez/mcp-ragchat
Add RAG-powered AI chat to any website with one command. Local vector store, multi-provider LLM (OpenAI/Anthropic/Gemini), self-contained chat server and embeddable widget.
end to end RAG platforms
zaharajabeen13-create/ai-rete-rag-mcp
Decisions the model doesn't make: a Rete rule engine returns the verdict, retrieval over your own policy documents explains it — so an explanation can't invent a threshold your rulebook doesn't have. Turn a written policy into draft rules that cite the sentence each encodes, save them as YAML, then decide; every verdict names the rule that fired, and you can ask why any rule didn't.
end to end RAG platforms
notwhiteblank/scholar-rag-mcp
Academic-paper knowledge base over local PDFs: MinerU parsing, metadata normalization, section annotation, Qdrant vector search with reranking, and context-safe paginated full-text reading. 11 tools including two-phase KB deletion; runs against local or OpenAI-compatible embedding/rerank/chat models (vLLM).