MCP Server Rememberizer

What is MCP Server Rememberizer about?

Provides a Model Context Protocol (MCP) server that exposes Rememberizer’s document and knowledge‑management capabilities to LLMs, allowing semantic retrieval, smart search, listing of integrations, account info access, and saving of new knowledge.

How to use MCP Server Rememberizer?

Installation – run uvx mcp-server-rememberizer (or install via the MseeP AI Helper app).
Configuration – set the environment variable REMEMBERIZER_API_TOKEN with your Rememberizer API token.
Integration – add the server definition to your Claude Desktop claude_desktop_config.json or configure the same env var in the MseeP AI Helper.
Invocation – call the provided tools (retrieve_semantically_similar_internal_knowledge, smart_search_internal_knowledge, list_internal_knowledge_systems, etc.) from any MCP‑compatible client.

Key features of MCP Server Rememberizer

Semantic retrieval of internal knowledge chunks by cosine similarity.
Agentic smart search across Slack, Gmail, Dropbox, Google Drive, and uploaded files.
Listing of all connected knowledge sources and paginated document enumeration.
Account‑information query for quick user details.
“Remember this” tool to store new information for future retrieval.
Simple environment‑variable based authentication.

Use cases of MCP Server Rememberizer

Context‑aware assistants: Provide real‑time answers from a company’s internal documents.
Knowledge bots: Retrieve past discussions, files, or emails during a conversation.
Personal knowledge base: Save ad‑hoc notes and have the model recall them later.
Enterprise search layer: Enable LLMs to query across multiple SaaS integrations without custom code.

FAQ from the MCP Server Rememberizer

Q: Do I need a Rememberizer account? A: Yes, an active account and an API token are required.

Q: Can I limit the date range of searches? A: Yes, optional from_datetime_ISO8601 and to_datetime_ISO8601 parameters filter results.

Q: How many results can I request? A: Use the n_results parameter; typical values are 3 (up to 5 results) or 10 for more detail.

Q: Is the server cross‑platform? A: The server runs wherever Python (via uvx) or the MseeP helper is available.

Q: How do I paginate document listings? A: Use page and page_size parameters on the list_personal_team_knowledge_documents tool.

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.

Please note that mcp-server-rememberizer is currently in development and the functionality may be subject to change.

Components

Resources

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

Tools

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 for which you wish to find semantically similar chunks of knowledge
  - n_results (integer, optional): Number of semantically similar chunks of text to return. Use 'n_results=3' for up to 5, and 'n_results=10' for more information
  - from_datetime_ISO8601 (string, optional): Start date in ISO 8601 format with timezone (e.g., 2023-01-01T00:00:00Z). Use this to filter results from a specific date
  - to_datetime_ISO8601 (string, optional): End date in ISO 8601 format with timezone (e.g., 2024-01-01T00:00:00Z). Use this to filter results until a specific date
- Returns: Search results as text output
smart_search_internal_knowledge
- Search for documents in Rememberizer in its personal/team internal knowledge and memory repository using a simple query that returns the results of an agentic search. The search may include sources such as Slack discussions, Gmail, Dropbox documents, Google Drive documents, and uploaded files
- Input:
  - query (string): Up to a 400-word sentence for which you wish to find semantically similar chunks of knowledge
  - user_context (string, optional): The additional context for the query. You might need to summarize the conversation up to this point for better context-awared results
  - n_results (integer, optional): Number of semantically similar chunks of text to return. Use 'n_results=3' for up to 5, and 'n_results=10' for more information
  - from_datetime_ISO8601 (string, optional): Start date in ISO 8601 format with timezone (e.g., 2023-01-01T00:00:00Z). Use this to filter results from a specific date
  - to_datetime_ISO8601 (string, optional): End date in ISO 8601 format with timezone (e.g., 2024-01-01T00:00:00Z). Use this to filter results until a specific date
- Returns: Search results as text output
list_internal_knowledge_systems
- List the sources of personal/team internal knowledge. These may include Slack discussions, Gmail, Dropbox documents, Google Drive documents, and uploaded files
- Input: None required
- Returns: List of available integrations
rememberizer_account_information
- Get information about your Rememberizer.ai personal/team knowledge repository account. This includes account holder name and email address
- Input: None required
- Returns: Account information details
list_personal_team_knowledge_documents
- Retrieves a paginated list of all documents in your personal/team knowledge system. Sources could include Slack discussions, Gmail, Dropbox documents, Google Drive documents, and uploaded files
- Input:
  - page (integer, optional): Page number for pagination, starts at 1 (default: 1)
  - page_size (integer, optional): Number of documents per page, range 1-1000 (default: 100)
- Returns: List of documents
remember_this
- Save a piece of text information in your Rememberizer.ai knowledge system so that it may be recalled in future through tools retrieve_semantically_similar_internal_knowledge or smart_search_internal_knowledge
- Input:
  - name (string): Name of the information. This is used to identify the information in the future
  - content (string): The information you wish to memorize
- Returns: Confirmation data

Installation

Manual Installation

uvx mcp-server-rememberizer

Via MseeP AI Helper App

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

MseeP AI Helper

Configuration

Environment Variables

The following environment variables are required:

REMEMBERIZER_API_TOKEN: Your Rememberizer API token

You can register an API key by creating your own Common Knowledge in Rememberizer.

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 MseeP AI Helper App

Add the env REMEMBERIZER_API_TOKEN to mcp-server-rememberizer.

MseeP AI Helper Configuration

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

What is my Rememberizer account?
List all documents that I have there.
Give me a quick summary about "..."
and so on...

To learn more about Rememberizer MCP Server: https://docs.rememberizer.ai/personal-use/integrations/rememberizer-mcp-servers

License

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

MCP Server Rememberizer