An AST-based MCP server that provides token-efficient codebase skeletons to LLM agents, reducing context token usage by 80-95% by exposing structural information instead of full source files.
Enables AI agents to efficiently read Python code by first providing file skeletons then fetching only needed implementations, reducing noise and cost.
Enables precise source code retrieval via tree-sitter AST parsing, cutting AI token costs by 86-99% by indexing codebases and fetching only needed symbols and structural queries (e.g., blast radius, importers) on demand.