MCP Server Memos: LLM Note Collaboration & Search

MCP Server Memos 📝: Let your LLMs chat with their memos! Seamlessly search, create, & manage notes via Python—because even AI needs sticky notes. 🧠✨" )

Visit Repository

✨ Developer Tools

4.0(167 reviews)

250 saves

116 comments

Ranked in the top 9% of all AI tools in its category

About MCP Server Memos

What is MCP Server Memos: LLM Note Collaboration & Search?

Think of this as your LLM's gateway to a self-hosted note-taking universe. Built on the Model Context Protocol (MCP), it lets large language models seamlessly interact with Memos servers—searching, creating, and managing notes with privacy controls. It’s like giving your AI a personal notepad that’s both secure and extensible.

How to Use MCP Server Memos: LLM Note Collaboration & Search?

Start by plugging it into your MCP setup. Drop the config snippet into your server YAML, tweak host/port/token values, and you’re good to go. Need more control? Install via Smithery for Claude Desktop or manually via pip. The CLI and Python library options let you mix-and-match how you deploy it—perfect for both quick prototypes and production workflows.

MCP Server Memos Features

Key Features of MCP Server Memos: LLM Note Collaboration & Search?

Keyword Magic: Instant search with natural language queries
Privacy-first: Public/protected/private visibility tiers for sensitive notes
Tag Mastery: Organize content with hierarchical tags
Secure Access: Token-based authentication for enterprise-grade security
API Flexibility: Create, retrieve, and manage memos programmatically

Use Cases of MCP Server Memos: LLM Note Collaboration & Search?

Researchers can auto-organize study findings, developers can document API experiments on-the-fly, and teams can share knowledge bases securely. The real win? Integrating with LLMs for smart note synthesis—like summarizing project updates from tagged memos or finding that one critical reference buried in your notes.

MCP Server Memos FAQ

FAQ from MCP Server Memos: LLM Note Collaboration & Search?

Q: Does it work with my favorite LLM?
A: Any MCP-compliant model—think Claude, Qwen, or custom models. The protocol handles the heavy lifting.

Q: Can I host it privately?
A: Absolutely! Designed for self-hosting with minimal dependencies. Just point it to your Memos server instance.

Q: What if I forget my access token?
A: Regenerate through your Memos server dashboard—no data loss, just a quick security reset.

Content

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