omer ayhan custom context mcp

WHAT IT CONNECTS

omer ayhan custom context mcp 为 AI Agent 提供什么

• Group and structure text based on JSON templates with placeholders
• Extract information from AI-generated text into structured JSON formats
• Support for any arbitrary JSON structure with nested placeholders
• Intelligent extraction of key-value pairs from text
• Process AI outputs into structured data for downstream applications
• **Define a JSON template with placeholders:**
• **Use `group-text-by-json` to create a prompt for AI:**
• The tool identifies placeholder keys: name, price, description
• Generates a prompt instructing the AI to group information by these keys
• **Send the prompt to an AI model and receive grouped text:**
• **Use `text-to-json` to convert the grouped text to JSON:**
• Result:
• Use angle brackets to define placeholders: `<name>`, `<type>`, `<price>`, etc.
• The template must be a valid JSON string
• Placeholders can be at any level of nesting
• Supports complex nested structures
• Analyzing JSON templates to extract placeholder keys
• Generating prompts that guide AI models to extract information by these keys
• Parsing AI-generated text to extract key-value pairs
• Reconstructing JSON objects based on the original template structure
• Node.js v18 or higher
• npm or yarn
• **nodemon**: Watches for file changes in the src directory and rebuilds TypeScript files
• **browser-sync**: Automatically refreshes the browser when build files change
• **Concurrent execution**: Runs both services simultaneously with output synchronization
• `nodemon.json`: Controls TypeScript watching and rebuilding
• `package.json`: Uses concurrently to run nodemon and browser-sync together
• TypeScript files are automatically rebuilt when changed
• The MCP server restarts with the updated code
• Connected browsers refresh to show the latest changes