MCP server that cuts LLM token costs: accurate token counting, cost estimates across GPT/Claude/Gemini, rule-based prompt slimming with
Free
Scanned where there is a package or repository to read, and every release diffed against the tool surface we already hold.
MCP server that cuts LLM token costs: accurate token counting, cost estimates across GPT/Claude/Gemini, rule-based prompt slimming with