Enables MCP-compatible agents such as Claude and Cursor to retrieve permission-aware, structured context from local or hosted data stores. Exposes tools for semantic search, entity and relationship lookup, memory access, context pack compilation, source attribution, and retrieval explanation.
Enables AI agents to read, write, search, and manage persistent, decentralized context memory via a GCS-backed MCP server, with tools for document storage, retrieval, and STIM protocol nuggets.