Memos Python
A Python package enabling LLM models to interact with the Memos server via the MCP interface for searching, creating, retrieving, and managing memos.
What is Memos Python?
Memos Python is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to python package enabling llm models to interact with the memos server via the mcp interface for searching, creating, retrieving, and managing memos.
A Python package enabling LLM models to interact with the Memos server via the MCP interface for searching, creating, retrieving, and managing memos.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Python package enabling LLM models to interact with the Me
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx memos-pyConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Memos Python
MCP Server Memos (Python) is a Python package that lets LLM models interact with a self-hosted Memos server through the Model Context Protocol. It exposes four tools — search_memo, create_memo, get_memo, and list_memo_tags — so AI assistants can search your notes by keyword, create new memos with configurable visibility (PUBLIC, PROTECTED, or PRIVATE), retrieve a specific memo by ID, and list all your tags. This is useful for anyone running a Memos instance who wants their AI assistant to act as a note-taking and retrieval layer.
Prerequisites
- A running Memos server (self-hosted at any URL, default port 8080 or 5230)
- A Memos access token (generated in Memos Settings → Access Tokens)
- Python 3.10 or higher, or uv/uvx installed for running the package
- An MCP-compatible client such as Claude Desktop or Claude Code
Set up your Memos server
You need a running Memos instance. If you do not have one, deploy it with Docker. The server must be accessible from the machine running this MCP server.
docker run -d --name memos -p 5230:5230 neosmemo/memos:stableGenerate a Memos access token
Log in to your Memos web UI, go to Settings → Access Tokens, and create a new token. Copy the token value — you will pass it as the --token argument.
Install the MCP server package
Install mcp-server-memos from PyPI using pip or uv. Using uvx lets you run it without a permanent install.
pip install mcp-server-memos
# or run directly without installing:
uvx --prerelease=allow mcp-server-memos --host localhost --port 5230 --token YOUR_ACCESS_TOKENAdd the server to your MCP client config
Register the server in your MCP client configuration, providing your Memos host, port, and access token as command-line arguments.
Test by searching your memos
Ask your AI client to search your memos to verify the connection. The search_memo tool accepts a keyword and returns matching memos.
Memos Python Examples
Client configuration
Add this to your MCP client config. Replace the host, port, and token values with your actual Memos server details.
{
"mcpServers": {
"memos": {
"command": "uvx",
"args": [
"--prerelease=allow",
"mcp-server-memos",
"--host", "localhost",
"--port", "5230",
"--token", "your-access-token-here"
]
}
}
}Prompts to try
Use your AI assistant to search, create, and retrieve memos from your Memos server.
- "Search my memos for notes about project deadlines."
- "Create a private memo: 'Remember to review the Q3 budget on Friday.'"
- "Get the memo with ID memos/42 and summarize it."
- "List all my memo tags and tell me which ones I use most."
- "Create a public memo with my weekly meeting notes."Troubleshooting Memos Python
Connection refused when the server starts
Verify your Memos server is running and accessible at the host and port you specified. Run curl http://localhost:5230/api/v1/memos to test connectivity before starting the MCP server.
Authentication errors (401 Unauthorized)
Your access token may be expired or incorrect. Generate a new token in Memos Settings → Access Tokens and update the --token argument in your MCP client config.
'mcp-server-memos' not found when using uvx
Add the --prerelease=allow flag as shown in the config example: uvx --prerelease=allow mcp-server-memos. Alternatively install with pip install mcp-server-memos and run using the mcp-server-memos command directly.
Frequently Asked Questions about Memos Python
What is Memos Python?
Memos Python is a Model Context Protocol (MCP) server that python package enabling llm models to interact with the memos server via the mcp interface for searching, creating, retrieving, and managing memos. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Memos Python?
Follow the installation instructions on the Memos Python GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Memos Python?
Memos Python works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Memos Python free to use?
Yes, Memos Python is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Memos Python Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Memos Python? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Memos Python in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Memos Python?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.