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.; codeTree: codetree is an MCP server that uses tree-sitter to provide structured code understanding to AI coding agents, reducing token usage by 25x. It offers 23 tools across 10 languages with startup around 1 second. No vector DB, embedding model, or configuration needed.
Deep repository research and analysis (e.g., architecture, contributors, issues)
Reduce token consumption for AI coding agents when exploring codebases