┌─────────────────────────────────────────────────────────────┐
│                    MCP Server Tools                         │
├─────────────────────────────────────────────────────────────┤
│  1. crawl_and_index(url_pattern, project_name)             │
│  2. list_projects()                                         │
│  3. search_documents(query, project_name, limit)           │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────┐
│                   Discovery Layer                           │
├─────────────────────────────────────────────────────────────┤
│  • Try sitemap.xml (fast)                                   │
│  • Try common doc patterns                                  │
│  • Crawl4AI recursive discovery (fallback)                  │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────┐
│                  Extraction Layer                           │
├─────────────────────────────────────────────────────────────┤
│  • Jina AI Reader API (primary, fast)                       │
│  • Crawl4AI (fallback for complex pages)                    │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────┐
│              Chunking & Embedding Layer                     │
├─────────────────────────────────────────────────────────────┤
│  • Smart text chunking                                      │
│  • OpenAI embeddings (text-embedding-3-small)               │
└─────────────────────────────────────────────────────────────┘
                            │
                            ▼
┌─────────────────────────────────────────────────────────────┐
│                   Supabase Storage                          │
├─────────────────────────────────────────────────────────────┤
│  • pgvector for similarity search                           │
│  • Project isolation via source column                      │
└─────────────────────────────────────────────────────────────┘

git clone https://github.com/yourusername/mcp-jina-supabase-rag.git
cd mcp-jina-supabase-rag

# Using uv (recommended)
uv venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
uv pip install -e .

# Or using pip
pip install -e .

# Run the SQL in supabase_schema.sql in your Supabase SQL Editor

cp .env.example .env
# Edit .env with your credentials

# SSE transport (recommended for remote connections)
python src/main.py

# The server will start on http://localhost:8052/sse

claude mcp add --transport sse jina-supabase http://localhost:8052/sse

{
  "mcpServers": {
    "jina-supabase": {
      "transport": "sse",
      "url": "http://localhost:8052/sse"
    }
  }
}

---
allowed-tools: mcp__jina-supabase
argument-hint: <url_pattern> <project_name>
description: Crawl documentation and index to Supabase RAG
---

# Index Documentation to Supabase

Use the jina-supabase MCP server to crawl and index documentation.

Arguments:
- $1: URL pattern (e.g., https://docs.example.com/*)
- $2: Project name for isolation

Example:
/jina https://docs.anthropic.com/claude/* anthropic-docs

await crawl_and_index(
    url_pattern="https://docs.supabase.com/docs/*",
    project_name="supabase-docs",
    discovery_method="auto",
    extraction_method="jina"
)

results = await search_documents(
    query="How do I set up authentication?",
    project_name="supabase-docs",
    limit=10
)

# Install dev dependencies
uv pip install -e ".[dev]"

# Run tests
pytest

# Format code
black src/

# Lint
ruff check src/