{
  "mcpServers": {
    "local-rag": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "github:RobThePCGuy/rag-vault"],
      "env": {
        "BASE_DIR": "/path/to/your/documents"
      }
    }
  }
}

{
  "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"
      }
    }
  }
}

claude mcp add local-rag --scope user --env BASE_DIR=/path/to/your/documents -- npx -y github:RobThePCGuy/rag-vault

[mcp_servers.local-rag]
command = "npx"
args = ["-y", "github:RobThePCGuy/rag-vault"]

[mcp_servers.local-rag.env]
BASE_DIR = "/path/to/your/documents"

# 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

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...

npx github:RobThePCGuy/rag-vault web

# 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 "file=@spec.pdf"

# 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"

# 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}'

# Start remote server (default port 3001)
npx github:RobThePCGuy/rag-vault --remote

# Custom port
npx github:RobThePCGuy/rag-vault --remote --port 8080

{
  "mcpServers": {
    "rag-vault-remote": {
      "type": "url",
      "url": "http://localhost:3001/mcp"
    }
  }
}

claude mcp add --transport http rag-vault http://localhost:3001/mcp

cloudflared tunnel --url http://localhost:3001

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...

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..."

Document → Parse → Chunk by meaning → Embed locally → Store in LanceDB
                         ↓
Query → Embed → Vector search + BM25 → Fusion → Optional reranking → Results