Provides an MCP server that guides AI agents through a mandatory three-stage SOP to compress prompts and report token costs, reducing token usage by up to 40%.
MCP server that minimizes LLM token usage by compressing, summarizing, filtering, chunk-referencing, and pruning large context before it reaches the model, with heuristic or local-SLM smart actions, caching, and token counting.
A remote MCP server that compresses long text contexts, stores compact reusable summaries, and retrieves relevant context by title/tag/query, helping reduce token usage.