Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y @robthepcguy/[email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
BASE_DIR=<value> DB_PATH=<value> CACHE_DIR=<value> MODEL_NAME=<value> RAG_HYBRID_WEIGHT=<value> RAG_GROUPING=<value> claude mcp add io.github.robthepcguy-rag-vault -- npx -y @robthepcguy/rag-vault@1.5.3รันในเทอร์มินัล
{ "mcpServers": { "io.github.robthepcguy-rag-vault": { "command": "npx", "args": [ "-y", "@robthepcguy/[email protected]" ], "env": { "BASE_DIR": "<value>", "DB_PATH": "<value>", "CACHE_DIR": "<value>", "MODEL_NAME": "<value>", "RAG_HYBRID_WEIGHT": "<value>", "RAG_GROUPING": "<value>" } } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Your documents. Your machine. Your control.
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.
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
One command to run, minimal setup, privacy by default.
RAG Vault comes with security built in:
RAG_API_KEYSee SECURITY.md for complete documentation.
Before adding MCP config:
BASE_DIR to that path.BASE_DIR.Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"local-rag": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:RobThePCGuy/rag-vault"],
"env": {
"BASE_DIR": "/path/to/your/documents"
}
}
}
}
Replace /path/to/your/documents with your real absolute path.
Add to .mcp.json in your project directory:
{
"mcpServers": {
"local-rag": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:RobThePCGuy/rag-vault"],
"env": {
"BASE_DIR": "./documents",
"DB_PATH": "./documents/.rag-db",
"CACHE_DIR": "./.cache",
"RAG_EMBEDDING_DEVICE": "cpu",
"RAG_HYBRID_WEIGHT": "0.6",
"RAG_GROUPING": "related"
}
}
}
}
Or add inline via CLI:
claude mcp add local-rag --scope user --env BASE_DIR=/path/to/your/documents -- npx -y github:RobThePCGuy/rag-vault
Add to ~/.codex/config.toml:
[mcp_servers.local-rag]
command = "npx"
args = ["-y", "github:RobThePCGuy/rag-vault"]
[mcp_servers.local-rag.env]
BASE_DIR = "/path/to/your/documents"
If you want your AI to write better queries and make more sense of results, install the RAG Vault skills:
# Claude Code (project-level - recommended for team projects)
npx github:RobThePCGuy/rag-vault skills install --claude-code
# Claude Code (user-level - available in all projects)
npx github:RobThePCGuy/rag-vault skills install --claude-code --global
# Codex (user-level)
npx github:RobThePCGuy/rag-vault skills install --codex
# Custom location
npx github:RobThePCGuy/rag-vault skills install --path /your/custom/path
Skills teach Claude best practices for:
ingest_file vs ingest_dataRestart your AI tool, and start talking:
You: "Ingest api-spec.pdf"
AI: Successfully ingested api-spec.pdf (47 chunks)
You: "How does authentication work?"
AI: Based on section 3.2, authentication uses OAuth 2.0 with JWT tokens...
That's it. No Docker. No Python. No server infrastructure to manage.
RAG Vault has a web UI so you can manage your documents without touching the command line.
npx github:RobThePCGuy/rag-vault web
Open http://localhost:3000 in your browser.
By default the web server binds to
127.0.0.1(loopback), so it is reachable only from this machine. To use it from another device on your network, setRAG_BIND_HOST=0.0.0.0— and setRAG_API_KEYas well, since the API is otherwise unauthenticated.
The web server has a REST API you can hit directly. Set RAG_API_KEY to require authentication:
# With authentication (when RAG_API_KEY is set)
curl -X POST "http://localhost:3000/api/v1/search" \
-H "Authorization: Bearer your-api-key" \
-H "Content-Type: application/json" \
-d '{"query": "authentication", "limit": 5}'
# Search documents (no auth needed if RAG_API_KEY isn't set)
curl -X POST "http://localhost:3000/api/v1/search" \
-H "Content-Type: application/json" \
-d '{"query": "authentication", "limit": 5}'
# List all files
curl "http://localhost:3000/api/v1/files"
# Upload a document
curl -X POST "http://localhost:3000/api/v1/files/upload" \
-F "[email protected]"
# Delete a file
curl -X DELETE "http://localhost:3000/api/v1/files" \
-H "Content-Type: application/json" \
-d '{"filePath": "/path/to/spec.pdf"}'
# Get system status
curl "http://localhost:3000/api/v1/status"
# Health check (for load balancers)
curl "http://localhost:3000/api/v1/health"
These endpoints let you read documents and find connections across them:
# Get all chunks for a document (ordered by index)
curl "http://localhost:3000/api/v1/documents/chunks?filePath=/path/to/doc.pdf"
# Find related chunks for cross-document discovery
curl "http://localhost:3000/api/v1/chunks/related?filePath=/path/to/doc.pdf&chunkIndex=0&limit=5"
# Batch request for multiple chunks (efficient for UIs)
curl -X POST "http://localhost:3000/api/v1/chunks/batch-related" \
-H "Content-Type: application/json" \
-d '{"chunks": [{"filePath": "/path/to/doc.pdf", "chunkIndex": 0}], "limit": 3}'
RAG Vault can also run as an HTTP server so remote MCP clients like Claude.ai, Claude Desktop, or anything that supports Streamable HTTP or SSE can connect to it.
# Start remote server (default port 3001)
npx github:RobThePCGuy/rag-vault --remote
# Custom port
npx github:RobThePCGuy/rag-vault --remote --port 8080
Stdio mode is unchanged. Just leave off --remote and everything works as before with Cursor, Claude Code, and Codex.
Add to your Claude Desktop config:
{
"mcpServers": {
"rag-vault-remote": {
"type": "url",
"url": "http://localhost:3001/mcp"
}
}
}
Or via Claude Code CLI:
claude mcp add --transport http rag-vault http://localhost:3001/mcp
For Claude.ai (Pro/Max/Team/Enterprise), add as a custom connector with URL https://your-host:3001/mcp. For local development, expose your server with a tunnel:
cloudflared tunnel --url http://localhost:3001
The remote server also binds to 127.0.0.1 (loopback) by default. To accept connections from other machines directly, set RAG_BIND_HOST=0.0.0.0. Set RAG_API_KEY for authentication whenever you expose the server beyond loopback (including via a tunnel). The server supports both Streamable HTTP (/mcp) and legacy SSE (/sse) transports, plus a health check at /health.
You: "Ingest all the markdown files in /docs"
AI: Ingested 23 files (847 chunks total)
You: "What's the retry policy for failed API calls?"
AI: According to error-handling.md, failed requests retry 3 times
with exponential backoff: 1s, 2s, 4s...
You: "Fetch https://docs.example.com/api and ingest the HTML"
AI: Ingested "docs.example.com/api" (156 chunks)
You: "What rate limits apply to the /users endpoint?"
AI: The API limits /users to 100 requests per minute per API key...
You: "Ingest my research papers folder"
AI: Ingested 12 PDFs (2,341 chunks)
You: "What do recent studies say about transformer attention mechanisms?"
AI: Based on attention-mechanisms-2024.pdf, the key finding is...
RAG Vault's hybrid search catches both meaning and exact matches:
You: "Search for ERR_CONNECTION_REFUSED"
AI: Found 3 results mentioning ERR_CONNECTION_REFUSED:
1. troubleshooting.md - "When you see ERR_CONNECTION_REFUSED..."
2. network-errors.pdf - "Common causes include..."
Pure semantic search would miss this. RAG Vault finds it.
Document → Parse → Chunk by meaning → Embed locally → Store in LanceDB
↓
Query → Embed → Vector search + BM25 → Fusion → Optional reranking → Results
Smart chunking: Splits by meaning, not character count. Keeps code blocks intact.
Hybrid search: Two fusion modes that combine vector similarity with BM25 keyword matching:
RAG_SEARCH_MODE=rrf): Reciprocal Rank Fusion treats vector and BM25 as independent voters. This can surface documents that vector search alone would miss.Cross-encoder reranking (opt-in): After the first pass, a cross-encoder model (Xenova/ms-marco-MiniLM-L-6-v2, ~23MB) scores each (query, passage) pair together for tighter relevance ranking. Turn it on with RAG_RERANKER_ENABLED=true.
Query expansion (opt-in): Generates reformulated queries to improve recall when searches are paraphrased or conceptual. Two backends: local template-based expansion (default, fully offline) or LLM-based HyDE through an external API. Turn it on with RAG_HYDE_ENABLED=true.
Quality filtering: Groups results by relevance gaps instead of arbitrary top-K cutoffs.
Local by default: Embeddings via Transformers.js. Storage via LanceDB. Network is only needed for initial model download or if you explicitly ingest remote URLs.
MCP tools included: query_documents, ingest_file, ingest_data, delete_file, list_files, status, feedback_pin, feedback_dismiss, and feedback_stats.
Windows users:
RAG_EMBEDDING_DEVICE=autotries GPU providers (DirectML), which can fail if ONNX Runtime GPU binaries aren't available. If you see embedding initialization errors, setRAG_EMBEDDING_DEVICE=cpuin your MCP config for reliable operation. See the GPU acceleration FAQ for details.
One-command override (no .env edit):
# MCP mode
npx github:RobThePCGuy/rag-vault --embedding-device cpu
# Web mode
npx github:RobThePCGuy/rag-vault web --embedding-device dml
# Explicitly force auto detection
npx github:RobThePCGuy/rag-vault --gpu-auto
Privacy note: The
apibackend sends query text to an external LLM endpoint, which breaks the "zero cloud" guarantee. The defaultrule-basedbackend is fully local.
Copy
.env.examplefor a complete configuration template.
For code-heavy content, try:
"env": {
"RAG_HYBRID_WEIGHT": "0.8",
"RAG_GROUPING": "similar"
}
For local files, yes. Indexing and search run on your machine after the embedding model downloads (~90MB). RAG Vault only hits the network if you choose remote URL ingestion or need to download a model.
Yes, after the first run. The model caches locally.
RAG Vault picks a device automatically by default (RAG_EMBEDDING_DEVICE=auto). When GPU providers are set up correctly, this can speed up embedding generation.
Important: On Windows, auto tries DirectML (dml), which requires ONNX Runtime GPU binaries. If those binaries aren't installed or your GPU setup is incomplete, the server won't start at all. It doesn't fall back to CPU gracefully. The same goes for Linux without CUDA binaries.
Recommendation: If you hit embedding initialization errors, set RAG_EMBEDDING_DEVICE=cpu in your MCP config. CPU mode is reliable on all platforms and fast enough for most workloads (the default model is only ~90MB).
"env": {
"RAG_EMBEDDING_DEVICE": "cpu"
}
Supported device values: auto, cpu, cuda, dml, gpu, wasm, webgpu, webnn, webnn-npu, webnn-gpu, webnn-cpu. The alias directml is also accepted and maps to dml.
Yes. Set MODEL_NAME to any compatible HuggingFace model. You'll need to delete DB_PATH and re-ingest because different models produce incompatible vectors.
Recommended upgrade: For better quality and multilingual support, use EmbeddingGemma:
"MODEL_NAME": "onnx-community/embeddinggemma-300m-ONNX"
It's a solid pick if you need multilingual support or higher-quality retrieval.
Other specialized models:
sentence-transformers/allenai-specterjinaai/jina-embeddings-v2-base-codeCopy the DB_PATH directory (default: ./lancedb/).
git clone https://github.com/RobThePCGuy/rag-vault.git
cd rag-vault
pnpm install
pnpm -C web-ui install
# Install local git hooks (recommended, even for solo dev)
pnpm hooks:install
# Fast local quality gate (backend + web-ui type/lint/format, deps, unused, build, unit tests)
pnpm check:all
# Unit tests only (no model download required)
pnpm test:unit
# Integration/E2E tests (requires model download/network)
pnpm test:integration
# Build
pnpm build
# Run MCP server locally (stdio)
pnpm dev
# Run MCP server locally (remote HTTP + SSE)
pnpm dev:remote
# Run web server locally
pnpm web:dev
# Release to npm (local, guarded)
pnpm release # patch
pnpm release:minor
pnpm release:major
pnpm release:dry
pnpm test:unit: deterministic tests for local/CI quality checks. Doesn't include model-download integration paths.pnpm test:integration: full integration and E2E workflows, including embedding model initialization.Use RUN_EMBEDDING_INTEGRATION=1 to explicitly opt into network/model-dependent suites.
scripts/release-npm.sh.patch, minor, major.pnpm check:all, and pnpm ui:build before touching version files.package.json and server.json versions only get updated after checks pass, and they're auto-restored if any later step fails.pnpm release:dry runs the full gate plus npm dry-run publish and always restores version files.src/
├── bin/ # CLI subcommands (skills install)
├── chunker/ # Semantic text splitting
├── embedder/ # Transformers.js wrapper
├── errors/ # Error handling utilities
├── explainability/ # Keyword-based result explanations
├── flywheel/ # Feedback loop (pin/dismiss reranking)
├── hyde/ # Query expansion + HyDE (LLM-based)
├── parser/ # PDF, DOCX, HTML parsing
├── query/ # Advanced query syntax parser
├── reranker/ # Cross-encoder reranking (Transformers.js)
├── server/ # MCP tool handlers + remote transport
├── utils/ # Config, file helpers, process handlers
├── vectordb/ # LanceDB + hybrid search (boost + RRF)
└── web/ # Express server + REST API
web-ui/ # React frontend (Vite + Tailwind)
MIT: free for personal and commercial use.
Built with Model Context Protocol, LanceDB, and Transformers.js.
Started as a fork of mcp-local-rag by Shinsuke Kagawa. Now it's its own thing. Huge credit to upstream contributors for the foundation, I've been iterating hard from there. Local-first dev tools, all the way.
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
{ "mcpServers": { "io.github.robthepcguy-rag-vault": { "command": "npx", "args": [ "-y", "@robthepcguy/[email protected]" ], "env": { "BASE_DIR": "<value>", "DB_PATH": "<value>", "CACHE_DIR": "<value>", "MODEL_NAME": "<value>", "RAG_HYBRID_WEIGHT": "<value>", "RAG_GROUPING": "<value>" } } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ผู้เผยแพร่ระบุตัวแปรสภาพแวดล้อมเหล่านี้: BASE_DIR, DB_PATH, CACHE_DIR, MODEL_NAME, RAG_HYBRID_WEIGHT, RAG_GROUPING
Rag Vault ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-09 Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup