io.github.RobThePCGuy/rag-vault MCP Server
io.github.RobThePCGuy/rag-vault
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.RobThePCGuy/rag-vault MCP server?
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
How to install io.github.RobThePCGuy/rag-vault
Copy-paste configuration for popular MCP clients.
BASE_DIRBase directory for document storage (defaults to current working directory)
DB_PATHPath to LanceDB database directory (defaults to ./lancedb/)
CACHE_DIRDirectory where Transformers.js models are cached (defaults to ./models/)
MODEL_NAMEEmbedding model name (defaults to Xenova/all-MiniLM-L6-v2)
RAG_HYBRID_WEIGHTKeyword boost strength for hybrid search. 0.0 = semantic only, 1.0 = keyword only. Default 0.6
RAG_GROUPINGGrouping mode: 'similar' (top group only) or 'related' (top 2 groups)
{
"mcpServers": {
"rag-vault": {
"command": "npx",
"args": [
"-y",
"@robthepcguy/rag-vault"
],
"env": {
"BASE_DIR": "<YOUR_BASE_DIR>",
"DB_PATH": "<YOUR_DB_PATH>",
"CACHE_DIR": "<YOUR_CACHE_DIR>",
"MODEL_NAME": "<YOUR_MODEL_NAME>",
"RAG_HYBRID_WEIGHT": "<YOUR_RAG_HYBRID_WEIGHT>",
"RAG_GROUPING": "<YOUR_RAG_GROUPING>"
}
}
}
}Related MCP servers
Crypto wallets, payments, and referral earnings for AI agents on Base L2
View repository →
Upspring
Live ads as reasoning-ready context, plus advertiser spend/traffic/sales scale grades over MCP.

AI Price Index
Read-only, zero-key MCP server for point-in-time AI model API prices. Open data, CC BY 4.0.
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

io.github.RobelDev/logclaw-mcp-server
Connect AI coding tools to LogClaw incidents, logs, and anomaly detections in your VPC.
UK Charity Commission register with cleaning - 31 tools for search, financials, governance.
View repository →

