aula-mcp: `aula-mcp` is a server that acts as an interface between a Model Context Protocol (MCP) client (LLM) and the Danish school communication platform Aula, facilitating data fetching from Aula. It explicitly states that the LLM is not part of the project, and data privacy relies entirely on the chosen client, with the server itself running locally and forwarding nothing independently.; headroom: Headroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. It achieves the same answers with a fraction of the tokens.
Enable LLMs to query Aula data (e.g., weekly schedules, messages) using natural language.
Reduce LLM token usage and API costs for AI agents.