MCP.so
登录

Remember Me MCP Server

@phlax

基本信息

分类

其他

许可证

GPL-3.0 license

传输方式

stdio

作者

phlax

关于 Remember Me MCP Server

MCP server to persist chat artefacts and rules

#mcp#chat-persistence#language-models

Remember Me MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "remember-me": {
      "command": "python",
      "args": [
        "-m",
        "mcp.server.run",
        "remember_me_mcp_server.server"
      ]
    }
  }
}

Remember Me MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Remember Me?

Remember Me is a persistence framework for maintaining conversational context and rules in MCP-based language model applications. It stores, retrieves, and manages persistent resources like rules, snippets, and summaries using SQLite, and is designed for developers building LLM applications that need durable context across conversations.

How to use Remember Me?

Install the package with pip install -e ., then run the MCP server with python -m mcp.server.run remember_me_mcp_server.server. Configure your LLM platform to connect to the MCP server and expose the tools. In conversations, the LLM should first load the context and then follow any rules returned.

Key features of Remember Me

  • Centralized context manager (MyContext) for all persistence operations
  • Rule system with MUST, MUST NOT, SHOULD, SHOULD NOT, and MAY policies
  • Snippet management for reusable code or text fragments
  • Summary management for preserving conversational context
  • Backup and restore of entire context states
  • Namespaced resources via “context” parameter (e.g., “me” for global)

Use cases of Remember Me

  • Defining behavior guidelines that an LLM must follow across all conversations
  • Storing reusable code snippets or text fragments for quick retrieval
  • Preserving important contextual summaries between chat sessions
  • Organizing different rule sets for different tasks (e.g., coding, creative writing)
  • Creating backups before making major changes to conversational state

常见问题

1

What is the “me” context?

The “me” context is a special default context always available. It contains global rules, snippets, and summaries that apply to every conversation. When loading context, the “me” context is always included automatically.

2

How do I load extra contexts beyond the “me” context?

You can load additional contexts by specifying them in the `extra_context` parameter. This allows organizing different sets of resources for different conversation types, such as a “coding” context with programming snippets.

3

What types of resources does Remember Me support?

Remember Me supports three resource types: Rules (behavior constraints), Snippets (reusable code or text fragments), and Summaries (important contextual information).

4

How do backup and restore work?

You can create a backup of the current state with `my_context_backup_create()`, list available backups with `my_context_backup_list()`, restore from a backup with `my_context_backup_restore()`, and remove backups individually or clear all with `my_context_backup_remove()` and `my_context_backup_clear()`.

5

What are the dependencies for running Remember Me?

The server runs on Python and uses SQLite for persistence. It communicates via the MCP protocol and requires an MCP‑compatible LLM platform to expose its tools.

评论

其他 分类下的更多 MCP 服务器