"Hyper" matching MCP servers:

Enables LLMs to manage vector collections, run hybrid semantic and Wasserstein searches, traverse knowledge graphs, and perform geometric and cognitive diagnostics through MCP tools. It also provides administration for caches, quantization, reconsolidation, and collection lifecycle operations.

Enables AI agents to store, recall, and self-maintain durable long-term memories on Cloudflare Workers using hybrid vector and full-text search with JEV-based re-ranking.

Enables AI coding assistants to answer HyperPay integration questions using an auto-refreshed index of the official developer documentation plus team notes. Supports hybrid keyword and semantic search, full page retrieval, result code explanations with recommended actions, and freshness checks on stale notes.

Enables AI coding agents to execute tools in a sandbox, retain searchable persistent memory, and reversibly compress long conversation histories through a unified MCP endpoint.

Enables coding agents to discover, optionally rank, and exactly read bounded source-addressed evidence from large repositories and noisy logs, with local-only privacy controls and quota-aware recovery.