📌Overview

Purpose: To enable LLM models to interact seamlessly with a Memos server using the Model Context Protocol (MCP).

Overview: MCP Server Memos is a Python package designed to facilitate the connection and communication between Large Language Models (LLMs) and a Memos server, simplifying memo search, creation, and management through a structured API.

Key Features:

Search Memos: Allows users to find specific memos using keywords for quick access.
Create Memos: Lets users create new memos with customizable visibility options, enhancing memo organization and privacy.
Retrieve Memo Content: Facilitates the retrieval of memo contents via memo ID, streamlining information access.
Manage Memo Tags: Provides functionality to list and manage tags associated with memos, aiding in better categorization.
Secure Authentication: Ensures secure access to memos through token-based authentication, protecting user data.

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

Include this package in your config file as below, similar to other Python MCP plugins:

{
  ...,
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    },
    "memos": {
      "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 owner of tags (format: memos/{id}, default: "memos/-") - `visibility`: Tag visibility (PUBLIC/PROTECTED/PRIVATE, default: PRIVATE)
`search_memo`	Search memos using keywords	- `key_word`: Keywords to search for in memo content
`create_memo`	Create a new memo	- `content`: Memo content - `visibility`: Memo visibility (PUBLIC/PROTECTED/PRIVATE, default: PRIVATE)
`get_memo`	Get a specific memo by ID	- `name`: 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.

🙏 Acknowledgments

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