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.; ckan-mcp-server: CKAN MCP Server turns any CKAN open data portal into a conversational AI assistant. It connects to the CKAN API and allows searching datasets, exploring organizations, querying tabular data, and reading metadata via natural language. The server can be installed locally or used via a hosted endpoint, and it works with many MCP-compatible clients like ChatGPT, Claude, and VS Code.
Deep repository research and analysis (e.g., architecture, contributors, issues)
Journalists looking for data to verify a story