A progressive-disclosure gateway for MCP servers that keeps tool lists small by exposing one top-level tool per server, allowing agents to search, list, inspect, and call underlying tools within a selected domain.
A configuration-driven framework for building MCP servers that expose domain-oriented tools (e.g., get_customer, get_database_sizes) instead of generic SQL interfaces, by loading tool metadata and SQL queries from declarative packs.
A lightweight and fast MCP server that enables AI agents to efficiently discover and execute tools through progressive disclosure, minimizing context consumption while supporting safe code execution in external environments.
A meta-MCP server that manages and aggregates other MCP servers, enabling LLMs to dynamically extend their own capabilities by searching for, adding, and configuring tool servers.
