About MCP Server Memos 📝
MCP Server Memos is a Python package that lets LLMs work with a Memos server through MCP for searching, creating, retrieving and managing memos. It is aimed at users who want their AI assistant to use Memos, and authenticates with an access token.
Key features
- 01Keyword search across memos
- 02Memo creation with configurable visibility
- 03Retrieve memo content by ID
- 04List and manage memo tags
- 05Access token authentication
Use cases
- 01Retrieving saved memos during an AI assistant conversation
- 02Letting an LLM record new content as Memos entries
- 03Organizing and reviewing memos by tag
MCP support
The project is an MCP server that exposes four tools, list_memo_tags, search_memo, create_memo and get_memo, to MCP clients for accessing a Memos server.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project 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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.