Charles-mcp: Charles MCP Server bridges Charles Proxy with MCP clients, enabling AI agents to read live traffic incrementally, analyze recorded sessions with structured summary-first output, and drill down into details. It supports real-time capture, history analysis, and a reverse engineering toolchain for decoding, replay, and signature discovery, all with token-budget optimized responses.; 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.
Real-time traffic monitoring and debugging for AI agents.
Deep repository research and analysis (e.g., architecture, contributors, issues)