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.; datawrapper-mcp: This MCP server allows AI assistants to create, publish, update, and display Datawrapper charts. It is built on the datawrapper Python library with Pydantic validation and supports multiple MCP clients like Claude and Codex.
Deep repository research and analysis (e.g., architecture, contributors, issues)
Creating and publishing charts from conversational data