{"id":1148,"slug":"woling-dev/promptthrift-mcp","name":"PromptThrift MCP","description":"Smart token compression for LLM apps. Save 70-90% on API costs with Gemma 4 local compression, multi-model cost tracking, and intelligent model routing.","category":"development","github":"https://github.com/woling-dev/promptthrift-mcp","homepage":"","server_url":"","transport":"http","install":[{"cmd":"pip install (recommended)**","imports":[]}],"tools":[{"name":"promptthrift_compress_history","description":"Compress old turns into a smart summary to reduce input tokens by 50-90%"},{"name":"promptthrift_count_tokens","description":"Track token usage and costs across 14 models"},{"name":"promptthrift_suggest_model","description":"Recommend the cheapest model for a given task to save 60-80% on simple tasks"},{"name":"promptthrift_pin_facts","description":"Pin critical facts that survive compression to never lose key context"}],"env_vars":["PROMPTTHRIFT_OLLAMA_URL"],"auth_type":"none","official":false,"stars":1,"status":"active","source":"mcpservers.org","created_at":"2026-05-25T07:28:47.904725+00:00","updated_at":"2026-05-25T17:31:06.709767+00:00","tags":[],"path":"promptthrift-mcp"}