MCP server that delegates mechanical tasks like summarization, classification, extraction, and drafting to a local Llama.cpp LLM, serving as a cost-optimization layer while Claude handles reasoning and quality control.
Local-first MCP server for versioning, searching, evaluating, and improving AI prompts. Agents can fetch prompts, report outcomes, add notes, and propose human-approved variations.
MCP server for audio transcription using local faster-whisper or OpenAI Whisper API, enabling multilingual transcription with optional GPT post-processing.