An MCP code-intelligence server for AI agents with pre-indexed AST cache, 62 MCP tools, and TOON-compressed output, enabling token-efficient code analysis and project health grading entirely locally.
Intelligent code indexing MCP server that saves 99% of tokens by retrieving exact function source via byte-offset seek. Provides 15 tools for symbol search, call graphs, and incremental indexing across 10 languages.
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.
An MCP server for semantic code search & navigation that helps AI agents work efficiently without burning through costly tokens. Instead of reading entire files, agents can search conceptually and jump directly to the specific functions, classes, and code chunks they need.
Local-first code intelligence MCP server that enables coding agents to search code, inspect structure, read exact ranges, and explore Git history with explicit token budgets.