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.; camofox-mcp: CamoFox MCP connects MCP clients to the CamoFox browser server, providing 47 automation tools with anti-detection capabilities. It supports multi-tab workflows, session persistence, and token-efficient accessibility snapshots. The toolset enables navigation, interaction, search, extraction, downloads, and batch operations.
Deep repository research and analysis (e.g., architecture, contributors, issues)
AI agents performing automated web testing and data extraction.