The two search modes do different jobs: the semantic one takes a passage and finds what resembles it, the smart search takes a question and works across mail, chat and documents at once - and what you learn can be written back into the same repository.
An MCP server over Rememberizer's document and knowledge API. It searches your personal or team knowledge repository two ways: semantic similarity against a block of text, and an agentic search from a plain query that reaches Slack discussions, Gmail, Dropbox, Google Drive and uploaded files. It also lists what is connected and saves new content back.
- Semantically similar passages for a block of up to 400 words, with an optional date range
- An agentic search across Slack, Gmail, Dropbox, Google Drive and uploaded files
- The knowledge systems currently connected
- The documents in your personal or team repository
- New content saved into the repository
- Your Rememberizer account details
- Documents and Slack discussions available as MCP resources
A Rememberizer account with your sources already connected - this searches what Rememberizer has indexed, so the integrations are configured there rather than here. The project describes itself as in development, with functionality subject to change.
One command plus a key — uvx mcp-server-rememberizer, then supply credentials