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.; gnosis-mcp: Gnosis MCP ingests documentation from local files, git history, and web crawls, making them searchable via MCP tools with hybrid keyword and semantic search. It supports SQLite and PostgreSQL backends, integrates with editors like Claude Code and VS Code, and requires zero configuration to start.
Deep repository research and analysis (e.g., architecture, contributors, issues)
AI agents query documentation to avoid hallucinations and get precise answers.