Skip to main content
Glama
by t2hnd
SETUP_INSTRUCTIONS.md4.41 kB
# Setup Instructions for Bakery Data MCP Server Follow these steps to set up the MCP server in Claude Desktop. ## Prerequisites - Python 3.10 or higher - Claude Desktop installed - The database has been created (by running `import_data.py`) ## Step 1: Verify Database Exists Make sure `bakery_data.db` exists in the project directory: ```bash ls -lh bakery_data.db ``` If it doesn't exist, run: ```bash source venv/bin/activate python import_data.py ``` ## Step 2: Test the MCP Server Locally (Optional) You can test that the server works: ```bash source venv/bin/activate python test_queries.py ``` This should display various query results from the database. ## Step 3: Configure Claude Desktop ### For macOS: 1. Open the Claude Desktop configuration file: ```bash open ~/Library/Application\ Support/Claude/claude_desktop_config.json ``` 2. Add the bakery-data server configuration: ```json { "mcpServers": { "bakery-data": { "command": "/Users/tatsuroh/Documents/2025_Yamanashi_GenAIWS/bakery_data_mcp/venv/bin/python", "args": [ "-m", "bakery_data_mcp.server" ], "cwd": "/Users/tatsuroh/Documents/2025_Yamanashi_GenAIWS/bakery_data_mcp" } } } ``` **Important**: If you already have other MCP servers configured, just add the `bakery-data` entry to the existing `mcpServers` object. ### For Windows: 1. Open the Claude Desktop configuration file at: ``` %APPDATA%\Claude\claude_desktop_config.json ``` 2. Add the bakery-data server configuration (adjust paths for Windows): ```json { "mcpServers": { "bakery-data": { "command": "C:\\Users\\YourUsername\\...\\bakery_data_mcp\\venv\\Scripts\\python.exe", "args": [ "-m", "bakery_data_mcp.server" ], "cwd": "C:\\Users\\YourUsername\\...\\bakery_data_mcp" } } } ``` ## Step 4: Restart Claude Desktop Completely quit Claude Desktop and restart it for the configuration to take effect. ## Step 5: Verify MCP Server is Running In Claude Desktop, you should see the MCP server indicator showing that "bakery-data" is connected. You can also check the MCP server tools by asking Claude: - "What MCP servers are available?" - "What tools does the bakery-data server provide?" ## Step 6: Test Queries Try asking Claude some questions about your bakery data: - "What are the top 10 selling products by revenue?" - "Show me sales summary for January 2024" - "Which products have the tag '朝食向け' (breakfast)?" - "What's the total revenue by department?" - "Show me transactions over ¥1000 in the last month of data" ## Troubleshooting ### Server Not Connecting 1. Check the paths in the config are absolute paths 2. Verify the virtual environment exists: `ls venv/bin/python` 3. Check Claude Desktop logs for errors ### Database Not Found Make sure the `cwd` in the configuration points to the directory containing `bakery_data.db`. ### Python Module Not Found Ensure the package is installed in the virtual environment: ```bash source venv/bin/activate pip install -e . ``` ## Available MCP Tools Once connected, Claude can use these tools: 1. **query_transactions** - Search and filter POS transactions 2. **query_products** - Search products by various criteria 3. **query_departments** - View department information 4. **sales_summary** - Get aggregated sales statistics 5. **top_products** - Find best-selling products 6. **execute_sql** - Run custom SQL queries 7. **get_schema** - View database schema and structure ## Example Configuration with Multiple Servers If you have other MCP servers, your config might look like: ```json { "mcpServers": { "filesystem": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/files"] }, "bakery-data": { "command": "/Users/tatsuroh/Documents/2025_Yamanashi_GenAIWS/bakery_data_mcp/venv/bin/python", "args": ["-m", "bakery_data_mcp.server"], "cwd": "/Users/tatsuroh/Documents/2025_Yamanashi_GenAIWS/bakery_data_mcp" } } } ``` ## Next Steps Once the server is running, you can: - Ask Claude to analyze sales trends - Generate reports on product performance - Query specific transaction details - Explore product categories and tags - Calculate department-level metrics

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/t2hnd/bakery_data_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server