Retrieve general information about an API, including endpoints, data models, and structure, to explore large OpenAPI schemas efficiently without loading entire schemas into LLM context.
Web scraper and token compressor that converts HTML to clean markdown with 70-80% fewer tokens. Single-page compression and multi-page BFS crawling with auto-fallback fetch modes.
LLM routing proxy that cuts API costs 60-90% by auto-selecting the cheapest capable model across OpenAI, Anthropic, and Google. Provides stats, config, and model comparison tools via MCP.
Provides LLMs with full PostgreSQL database access, including tools for query execution, schema management, and data export. It also features a dedicated insights system for storing business memos and supports both local stdio and remote HTTP transport.