A local RAG context optimizer MCP server that filters retrieved context to the minimum an LLM needs to answer correctly, using a cross-encoder and optional calibration.
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.
MCP server for deterministic, zero-dependency context-window math, enabling token estimation, text truncation, and budget reporting without a tokenizer.