Memos MCP Server

Memos MCP Server

Enables AI assistants to interact with Memos instances, supporting multi-instance connections, note management, tags, attachments, and shortcuts.

Category
Visit Server

README

Memos MCP Server

A Model Context Protocol (MCP) server for Memos, enabling AI assistants to interact with your Memos instances.

Features

  • 🔗 Multi-Instance Support: Connect to multiple Memos instances and query them individually or collectively
  • 📝 Note Management: Create, read, update, and delete memos with full Markdown support
  • 🏷️ Tag Management: List and manage tags across your memos
  • 📎 Attachment Support: Upload and manage file attachments
  • 🔖 Shortcuts: Create and manage saved filters
  • 🔒 Secure Storage: API keys are stored locally in your configuration directory
  • 🎚️ Tiered Tool Exposure: Control which tools are enabled to minimize context usage

Usage

With Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "memos": {
      "command": "npx",
      "args": ["-y", "@0xlimao/memos-mcp-server"]
    }
  }
}

Tool Tiers

The server supports three tiers of tools to minimize context usage:

Tier Flag Description
Tier 1 (default) Core note-taking tools
Tier 2 --user-tools User advanced features (PAT, webhooks)
Tier 3 --admin-tools Instance administration
All --full-tools All tools enabled

Example configurations:

// Default: Only note-taking tools
{
  "command": "npx",
  "args": ["-y", "@0xlimao/memos-mcp-server"]
}

// With user advanced tools
{
  "command": "npx",
  "args": ["-y", "@0xlimao/memos-mcp-server", "--user-tools"]
}

// With admin tools
{
  "command": "npx",
  "args": ["-y", "@0xlimao/memos-mcp-server", "--admin-tools"]
}

// All tools
{
  "command": "npx",
  "args": ["-y", "@0xlimao/memos-mcp-server", "--full-tools"]
}

Configuration File Location

Instance configurations are stored at:

  • macOS/Linux: ~/.config/memos-mcp/instances.json
  • Windows: %APPDATA%\memos-mcp\instances.json

Available Tools

Tier 1: Core Tools (Default)

Tool Description
connect_instance Connect to a new Memos instance
disconnect_instance Remove a connected instance
list_instances List all connected instances
list_memos List memos with optional filtering
get_memo Get a specific memo by ID
create_memo Create a new memo
update_memo Update an existing memo
delete_memo Delete a memo
list_tags List all tags
list_shortcuts List saved shortcuts
create_shortcut Create a new shortcut
update_shortcut Update a shortcut
delete_shortcut Delete a shortcut
list_attachments List attachments
upload_attachment Upload a new attachment
delete_attachment Delete an attachment

Tier 2: User Advanced Tools (--user-tools)

Tool Description
list_personal_access_tokens List PATs for a user
create_personal_access_token Create a new PAT
delete_personal_access_token Delete a PAT
list_webhooks List webhooks for a user
create_webhook Create a new webhook
update_webhook Update a webhook
delete_webhook Delete a webhook
get_user_setting Get user settings
update_user_setting Update user settings
list_user_settings List all user settings
list_notifications List user notifications
update_notification Update a notification
delete_notification Delete a notification

Tier 3: Admin Tools (--admin-tools)

Tool Description
list_users List all users
get_user Get a specific user by ID or username
create_user Create a new user
update_user Update a user
delete_user Delete a user
get_instance_profile Get instance information
get_instance_setting Get instance settings
update_instance_setting Update instance settings
list_activities List activities
get_activity Get a specific activity

Examples

Connecting to a Memos Instance

"Connect to my Memos instance at https://memos.example.com with the API key abc123"

The AI will use the connect_instance tool to save the connection:

  • Host: https://memos.example.com
  • Name: A friendly name (e.g., personal, work)
  • API Key: Your access token from Memos → Settings → My Account → Access Tokens

Searching Across All Instances

"Find all memos containing 'project ideas' in all my memos instances"

The server will query all connected instances and return matching results.

Querying a Specific Instance

"Create a new memo in my work-memos instance about the meeting today"

The server will create the memo only in the specified instance.

Using Filters

"List all archived memos with the #important tag"

The server supports CEL filter expressions for advanced queries.

Development

# Clone the repository
git clone https://github.com/flyinglimao/mcp-server-memos.git
cd mcp-server-memos

# Install dependencies
pnpm install

# Run in development mode
pnpm run dev

# Run tests
pnpm test

# Lint code
pnpm run lint

# Format code
pnpm run format

License

MIT License - see LICENSE for details.

Contributing

Contributions are welcome! Please read our contributing guidelines before submitting PRs.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured