Documentation
Memrio is a remote MCP server in front of a knowledge base people govern. These pages cover the model, the endpoint, every tool, and how to write pages agents use well.
Memrio is a human-governed knowledge base that AI agents read over MCP. Learn the model: workspaces, pages, page sets, agents, keys, and review.
ReadGo from an empty Memrio workspace to an agent answering from an approved page in about ten minutes.
ReadEvery tool Memrio exposes over MCP: browse, search_pages, get_page, and the write tools get_page_source, create_page, update_page, append_to_page.
ReadThe markdown dialect agents and people use to write Memrio pages, including instruction, fact, callout, and fields blocks.
ReadHow review and publishing work in Memrio, and what each agent permission — read drafts, can edit, can publish — actually allows.
ReadA copy-paste system prompt that teaches any AI agent how to use Memrio well: browse first, open pages, answer only from them.
ReadWhere to find Memrio documentation in formats built for language models: /llms.txt, /llms-full.txt, and per-page markdown.
Read