PoetryQuill Analytics MCP

An MCP server that connects Claude Desktop to PoetryQuill's live Supabase database. Ask Claude natural language questions about your platform data.

Setup

1. Install dependencies

pip install mcp supabase python-dotenv

2. Configure credentials

cp .env.example .env

Edit .env and add your Supabase URL and service role key

3. Run the simulator (optional — adds realistic demo data)

python simulate_poetryquill.py

4. Connect to Claude Desktop

Add to ~/.config/Claude/claude_desktop_config.json:

{ "mcpServers": { "poetryquill": { "command": "python", "args": ["/full/path/to/server.py"] } } }

5. Restart Claude Desktop

Look for the hammer icon — your tools are connected.

Related MCP server: Supabase MCP Server

Example questions to ask Claude

• "Give me a platform overview of PoetryQuill"

• "What are the top 10 most liked poems?"

• "Who are the most followed authors?"

• "Analyze engagement trends over the last 30 days"

• "What tags are writers using most?"

• "Show me the user growth over the last 90 days"

• "Which collections have the most poems?"

• "Analyze a sample of recent poems and tell me what themes are trending"

• "Who has the longest writing streak?"

• "Where are our users from?"

Tools available

Schema

Built for PoetryQuill's Supabase schema: profiles, poems, likes, comments, follows, collections, collection_poems