"author:ArtemKyslicyn" matching MCP servers:

Enables indexing a folder of documents or uploaded files into a Qdrant vector store and retrieving relevant chunks with cosine similarity, metadata filters, and heuristic reranking. Exposes rag_stats, rag_search, and rag_index tools over HTTP and Streamable HTTP MCP so clients can fetch ready-to-use context blocks without any built-in chat model.

Enables users to attach child MCP servers, run sandboxed Python, and transfer large outputs via artifacts through one authenticated Streamable HTTP endpoint exposed by tunnel to a cloud chat client.

Enables probing a live AI stand's health and latency, retrieving model Pareto and down-votes, and scheduling recurring digest summaries.