MCP Server Rememberizer

一个用于与Rememberizer的文档和知识管理API交互的模型上下文协议服务器。该服务器使大型语言模型能够通过Rememberizer搜索、检索和管理文档及集成。

请注意，mcp-server-rememberizer 目前正在开发中，其功能可能会发生变化。

组件

资源

服务器提供了两种类型的资源访问：文档或Slack讨论

工具

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 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

2. 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

3. 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

4. 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

5. 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

6. 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

安装

通过 mcp-get.com

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

通过 Smithery

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

通过 SkyDeck AI Helper 应用程序

如果你已安装了 SkyDeck AI Helper 应用程序，你可以搜索 "Rememberizer" 并安装 mcp-server-rememberizer。

配置

环境变量

需要以下环境变量：

• REMEMBERIZER_API_TOKEN: 你的 Rememberizer API 令牌

你可以在 Rememberizer 中创建自己的通用知识 来注册一个 API 密钥。

在 Claude Desktop 中使用

将以下内容添加到你的 claude_desktop_config.json 文件中：

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

在 SkyDeck AI Helper 应用程序中使用

将环境变量 REMEMBERIZER_API_TOKEN 添加到 mcp-server-rememberizer 中。

在 Rememberizer MCP 服务器的支持下，你现在可以在你的 Claude Desktop 应用或 SkyDeck AI GenStudio 中询问以下问题：

• 我的 Rememberizer 账号是什么？

• 列出我所有的文档。

• 给我关于“...”的快速摘要

• 等等...

许可证

本项目根据 Apache License 2.0 许可 - 详情请参阅 LICENSE 文件。