mcp-server-memos-py MCP Server

README

MCP Server Memos 📝

A Python package that provides LLM models with the ability to interact with Memos server through the MCP (Model Context Protocol) interface.

🚀 Features

🔍 Search memos with keywords
✨ Create new memos with customizable visibility
📖 Retrieve memo content by ID
🏷️ List and manage memo tags
🔐 Secure authentication using access tokens

🛠️ Usage

You can include this package in your config file as bellow, just as you use other Python MCP plugins.

{
  ...,
  "mcpServers": {
    "fetch": { // other mcp servers
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    },
    "memos": { // add this to your config
      "command": "uvx",
      "args": [
        "--prerelease=allow",
        "mcp-server-memos",
        "--host",
        "localhost",
        "--port",
        "5230",
        "--token",
        "your-access-token-here"
      ]
    }
  }
}

Other ways to use this package

📦 Installation

Installing via Smithery

To install mcp-server-memos-py for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @RyoJerryYu/mcp-server-memos-py --client claude

Installing Manually

pip install mcp-server-memos

Command Line

mcp-server-memos --host localhost --port 8080 --token YOUR_ACCESS_TOKEN

As a Library

from mcp_server_memos import Config, serve_stdio

config = Config(
    host="localhost",
    port=8080,
    token="YOUR_ACCESS_TOKEN"
)

await serve_stdio(config=config)

🔧 Configuration

Parameter	Description	Default
`host`	Memos server hostname	`localhost`
`port`	Memos server port	`8080`
`token`	Access token for authentication	`""`

🤝 Available Tools

This MCP server provides the following tools for interacting with Memos:

Tool Name	Description	Parameters
`list_memo_tags`	List all existing memo tags	- `parent`: The parent who owns the tags (format: memos/{id}, default: "memos/-") - `visibility`: Tag visibility (PUBLIC/PROTECTED/PRIVATE, default: PRIVATE)
`search_memo`	Search for memos using keywords	- `key_word`: The keywords to search for in memo content
`create_memo`	Create a new memo	- `content`: The content of the memo - `visibility`: Memo visibility (PUBLIC/PROTECTED/PRIVATE, default: PRIVATE)
`get_memo`	Get a specific memo by ID	- `name`: The name/ID of the memo (format: memos/{id})

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

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

🙏 Acknowledgments

Memos - A lightweight, self-hosted memo hub
MCP (Model Context Protocol) - Protocol for LLM model applications

mcp-server-memos-py FAQ

How do I authenticate with the mcp-server-memos-py?

Authentication is handled securely using access tokens, ensuring only authorized LLMs can access or modify memos.

Can I create memos with different visibility settings?

Yes, the server supports creating memos with customizable visibility to control who can view them.

How does the server handle searching memos?

It allows keyword-based search to quickly find relevant memos stored on the Memos server.

Is it possible to manage memo tags through this MCP server?

Yes, you can list and manage tags associated with memos to organize content effectively.

What programming language is mcp-server-memos-py written in?

It is a Python package designed for easy integration with Python-based LLM clients.

Does mcp-server-memos-py support real-time interaction with LLMs?

Yes, it uses the Model Context Protocol to provide real-time, structured context for LLMs.

Where can I find the source code and documentation?

The source code and documentation are available on GitHub at https://github.com/RyoJerryYu/mcp-server-memos-py.

Can this server be used with multiple LLM providers?

Yes, it is provider-agnostic and works with models like OpenAI, Claude, and Gemini.