indxr: indxr gives AI coding agents a structural map of codebases, reducing token costs by ~5x compared to reading full files. It supports 27 languages, provides a 22-tool MCP server for live queries, and features incremental caching, git structural diffing, and dependency graphs. Setup is one-command with `indxr init` for popular AI coding agents.; context-mode: Every tool call in an MCP (Model-Controller-Program) environment dumps raw data into the context window, quickly consuming space and causing the agent to lose track of ongoing tasks. Context Mode is an MCP server that tackles this by sandboxing tool outputs to significantly reduce context usage, tracking session events in SQLite for continuity, and promoting 'think in code' to minimize data processing within the LLM.
AI coding agents understanding a codebase without full file reads
Deep repository research and analysis (e.g., architecture, contributors, issues)