Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
RAG Vault lets your AI coding assistant search your private documents, things like API specs, research papers, and internal docs. Everything runs locally and your data stays on your machine unless you choose to pull in content from a remote URL.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"local-rag": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:RobThePCGuy/rag-vault"],
"env": {
"BASE_DIR": "/path/to/your/documents"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| BASE_DIR | Filesystem location the server is allowed to use. | Optional |
| DB_PATH | Filesystem location the server is allowed to use. | Optional |
| CACHE_DIR | Filesystem location the server is allowed to use. | Optional |
| RAG_EMBEDDING_DEVICE | Configuration value read at startup. | Optional |
| RAG_HYBRID_WEIGHT | Configuration value read at startup. | Optional |
| RAG_GROUPING | Configuration value read at startup. | Optional |
| MODEL_NAME | Configuration value read at startup. | Optional |
| RAG_API_KEY | Credential the server authenticates with. | Yes |
Generates both vector and raster images using EverArt's AI models, providing flexible storage and format conversion.
Provides file system operations, analysis, and manipulation through a standardized tool interface.
Extract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.
An MCP server that gives AI assistants structured access to XRP Ledger data and network actions.
CortexScout is the Deep Research & Web Extraction module within the Cortex-Works ecosystem.
Parse, extract, split, and ask over digital PDFs (text layer, no OCR) from Cursor and Claude.