📌Overview

Purpose: To enable Large Language Models to effectively search, retrieve, and manage documents and knowledge via Rememberizer's API.

Overview: The mcp-server-rememberizer is a Model Context Protocol server designed to facilitate interaction with Rememberizer's document and knowledge management system. While in development, it offers features targeting advanced search capabilities and integration management.

Key Features:

• rememberizer_search: Provides semantic search functionality to find documents based on a given query, enhancing content discovery by matching semantic similarities.

• rememberizer_agentic_search: Enhances the search process by leveraging LLM Agents for better contextual results, allowing more sophisticated searches with user-defined context.

• rememberizer_list_integrations: Lists available data source integrations for easy access to connected services without additional input.

• rememberizer_account_information: Retrieves account-specific information, providing essential details without requiring user input.

• rememberizer_list_documents: Facilitates the retrieval of a paginated list of all documents, supporting efficient document management and browsing.

---

MCP Server Rememberizer

A Model Context Protocol server for interacting with Rememberizer's document and knowledge management API. This server enables Large Language Models to search, retrieve, and manage documents and integrations through Rememberizer.

Note: mcp-server-rememberizer is currently in development and functionality may change.

Components

Resources

The server provides access to two types of resources: Documents or Slack discussions.

Tools

1. retrieve_semantically_similar_internal_knowledge

   • Send a block of text and retrieve cosine similar matches from your connected Rememberizer personal/team internal knowledge and memory repository.
   • Input:
     • match_this (string): Up to a 400-word sentence to find semantically similar chunks.
     • n_results (integer, optional): Number of similar chunks to return (e.g., 3 or 10).
     • from_datetime_ISO8601 (string, optional): Start date filter (ISO 8601 format with timezone).
     • to_datetime_ISO8601 (string, optional): End date filter (ISO 8601 format with timezone).
   • Returns: Search results as text.

2. smart_search_internal_knowledge

   • Searches in Rememberizer’s personal/team knowledge repository using a query, covering sources such as Slack, Gmail, Dropbox, Google Drive, and uploaded files.
   • Input:
     • query (string): Up to 400 words to search.
     • user_context (string, optional): Additional context to improve results.
     • n_results (integer, optional): Number of results to return.
     • from_datetime_ISO8601 (string, optional): Start date filter.
     • to_datetime_ISO8601 (string, optional): End date filter.
   • Returns: Search results as text.

3. list_internal_knowledge_systems

   • Lists the sources of personal/team internal knowledge (Slack, Gmail, Dropbox, Google Drive, uploaded files).
   • Input: None.
   • Returns: List of integrations.

4. rememberizer_account_information

   • Retrieves information about your Rememberizer.ai personal/team knowledge repository account (e.g., name, email).
   • Input: None.
   • Returns: Account information.

5. list_personal_team_knowledge_documents

   • Retrieves a paginated list of documents in your personal/team knowledge system.
   • Input:
     • page (integer, optional): Page number (default: 1).
     • page_size (integer, optional): Number of documents per page (default: 100, range 1-1000).
   • Returns: List of documents.

6. remember_this

   • Saves a piece of text information in your Rememberizer.ai knowledge system.
   • Input:
     • name (string): Identifier name for the information.
     • content (string): Content to memorize.
   • Returns: Confirmation.

Installation

Via mcp-get.com

npx @michaellatman/mcp-get@latest install mcp-server-rememberizer

Via Smithery

npx -y @smithery/cli install mcp-server-rememberizer --client claude

Via SkyDeck AI Helper App

If you have the SkyDeck AI Helper app installed, you can search for Rememberizer and install mcp-server-rememberizer.

Configuration

Environment Variables

• REMEMBERIZER_API_TOKEN: Your Rememberizer API token.

Register an API key by creating your own Common Knowledge in Rememberizer: https://docs.rememberizer.ai/developer/registering-and-using-api-keys

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

"mcpServers": {
  "rememberizer": {
      "command": "uvx",
      "args": ["mcp-server-rememberizer"],
      "env": {
        "REMEMBERIZER_API_TOKEN": "your_rememberizer_api_token"
      }
    }
}

Usage with SkyDeck AI Helper App

Add the environment variable REMEMBERIZER_API_TOKEN to the mcp-server-rememberizer configuration.

With support from the Rememberizer MCP server, you can now ask questions in your Claude Desktop app or SkyDeck AI GenStudio such as:

• What is my Rememberizer account?
• List all documents that I have there.
• Give me a quick summary about "..."
• And more.

License

This project is licensed under the Apache License 2.0. See the LICENSE file for details.