MCP Memos
A Python package that enables LLM models to interact with Memos server through the Model Context Protocol interface, allowing search, creation, retrieval, and management of memos.
What is MCP Memos?
MCP Memos is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to python package that enables llm models to interact with memos server through the model context protocol interface, allowing search, creation, retrieval, and management of memos.
A Python package that enables LLM models to interact with Memos server through the Model Context Protocol interface, allowing search, creation, retrieval, and management of 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 that enables LLM models to interact with Me
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-server-memosConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Memos
The MCP Server Memos package connects LLM assistants to a self-hosted Memos server (usememo.com) via the Model Context Protocol, enabling Claude and other MCP clients to search, create, retrieve, and tag memos without leaving the conversation. It exposes four tools — list_memo_tags, search_memo, create_memo, and get_memo — and supports Memos visibility levels (PRIVATE, PROTECTED, PUBLIC) so notes go to the right audience. Developers and knowledge workers who run their own Memos instance can use this to build an AI-assisted personal knowledge base where Claude can store and recall notes on demand.
Prerequisites
- A running Memos server instance (self-hosted, e.g. at http://localhost:5230)
- A Memos access token from your Memos account settings
- Python 3.9 or later with pip or uv installed
- An MCP-compatible client such as Claude Desktop
Install mcp-server-memos via pip
Install the package from PyPI. The package name on PyPI is mcp-server-memos.
pip install mcp-server-memosGet your Memos access token
Log in to your Memos instance, go to Settings → Profile, and generate an access token. Copy this token — you will need it for the server configuration.
Add the server to Claude Desktop config
Configure the server with your Memos host, port, and access token. The default port for Memos is 5230. Pass these as command-line arguments to the uvx command.
{
"mcpServers": {
"memos": {
"command": "uvx",
"args": [
"--prerelease=allow",
"mcp-server-memos",
"--host", "localhost",
"--port", "5230",
"--token", "your-access-token-here"
]
}
}
}Restart Claude Desktop
Fully quit and reopen Claude Desktop. The four Memos tools (list_memo_tags, search_memo, create_memo, get_memo) should now be available in your conversations.
Test the connection
Ask Claude to list your memo tags or search for a keyword to confirm the server can reach your Memos instance.
MCP Memos Examples
Client configuration
Claude Desktop configuration connecting to a local Memos instance on port 5230 with a personal access token.
{
"mcpServers": {
"memos": {
"command": "uvx",
"args": [
"--prerelease=allow",
"mcp-server-memos",
"--host", "localhost",
"--port", "5230",
"--token", "your-memos-access-token"
]
}
}
}Prompts to try
Example prompts that exercise the four Memos tools for search, creation, and retrieval.
- "Search my memos for notes about the project architecture decisions"
- "Create a new private memo with today's meeting notes: [paste notes here]"
- "List all memo tags I've used and tell me which topics I write about most"
- "Get memo memos/abc123 and summarize it for me"
- "Create a public memo summarizing the key takeaways from our discussion"Troubleshooting MCP Memos
Connection refused or timeout errors when tools try to reach Memos
Verify your Memos server is running and accessible at the host/port you configured. Try curl http://localhost:5230/api/v1/memo in a terminal. If using a remote Memos instance, replace localhost with the correct hostname or IP.
Authentication errors or 401 responses from Memos
Regenerate your access token in Memos Settings → Profile and update the --token argument in your config. Tokens may expire or be revoked if you change your password.
Smithery installation alternative if pip install fails
Install via Smithery CLI: npx -y @smithery/cli install @RyoJerryYu/mcp-server-memos-py --client claude. This automates the config setup and may resolve dependency conflicts.
Frequently Asked Questions about MCP Memos
What is MCP Memos?
MCP Memos is a Model Context Protocol (MCP) server that python package that enables llm models to interact with memos server through the model context protocol interface, allowing search, creation, retrieval, and management of memos. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Memos?
Follow the installation instructions on the MCP Memos GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Memos?
MCP Memos works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Memos free to use?
Yes, MCP Memos is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
MCP Memos Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to MCP Memos? 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 MCP Memos 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 MCP Memos?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.