A discovery and routing layer for MCP servers that loads tool definitions on demand, reducing token usage by keeping servers out of the context window until needed.
Routes SKILL.md libraries to any MCP client, enabling task matching and skill loading with embedding-based scoring, keyword fallback, and context-window discipline.
Enables agents to use many MCP servers without context bloat by exposing meta-tools (search, load, call, run_code) that reduce token usage via progressive disclosure and result trimming.
A lazy router for Claude Code skills that exposes a library of skills through search, load, and reindex MCP tools, reducing context usage by only loading skills on demand.