Memos MCP Server
An MCP (Model Context Protocol) server that provides tools for interacting with a Memos instance. This server allows AI assistants to search, create, and update memos through the Memos API.
Features
Search Memos: Search for memos with filters like creator, tags, visibility, and content
Create Memos: Create new memos with markdown support
Update Memos: Update existing memos (content, visibility, pinned status)
Get Memo: Retrieve a specific memo by UID
Installation
Clone this repository:
Install dependencies:
Using uv (recommended)
Using pip
Configuration
Set the following environment variables:
MEMOS_BASE_URL
: The base URL of your Memos instance (default:http://localhost:5230
)MEMOS_API_TOKEN
: Your Memos API authentication token (optional for public instances)
Getting an API Token
Log into your Memos instance
Go to Settings → Access Tokens
Create a new access token
Copy the token and set it as the
MEMOS_API_TOKEN
environment variable
Example:
Usage
Running the Server
Using uvx (no installation required)
Using uv after installation
Using FastMCP directly
Programmatic usage
Available Tools
1. search_memos
Search for memos with optional filters.
Parameters:
query
(optional): Text to search for in memo contentcreator_id
(optional): Filter by creator user IDtag
(optional): Filter by tag namevisibility
(optional): Filter by visibility (PUBLIC, PROTECTED, PRIVATE)limit
(default: 10): Maximum number of resultsoffset
(default: 0): Number of results to skip
Example:
2. create_memo
Create a new memo.
Parameters:
content
: The content of the memo (supports Markdown)visibility
(default: PRIVATE): Visibility level (PUBLIC, PROTECTED, PRIVATE)
Example:
3. update_memo
Update an existing memo.
Parameters:
memo_uid
: The UID of the memo to updatecontent
(optional): New content for the memovisibility
(optional): New visibility levelpinned
(optional): Whether to pin the memo
Example:
4. get_memo
Get a specific memo by its UID.
Parameters:
memo_uid
: The UID of the memo to retrieve
Example:
Integration with MCP Clients
Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Using uvx (recommended - no installation needed)
Using uv (after installation)
Using Python directly
API Reference
This server is built on the Memos API v1. The API follows Google's API Improvement Proposals (AIPs) design guidelines.
API Endpoints Used
GET /api/v1/memos
- List/search memosPOST /api/v1/memos
- Create a memoGET /api/v1/memos/{uid}
- Get a specific memoPATCH /api/v1/memos/{uid}
- Update a memo
Authentication
The server supports Bearer token authentication. Include your access token in the Authorization
header:
Development
Running Tests
Code Structure
server.py
: Main MCP server implementation with all toolsrequirements.txt
: Python dependencies
About Memos
Memos is a lightweight, self-hosted memo hub with knowledge management and social networking features. Learn more at:
Website: https://www.usememos.com/
License
MIT License - see LICENSE file for details
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables AI assistants to interact with Memos instances for knowledge management. Supports searching, creating, updating, and retrieving memos with markdown content, tags, and visibility controls.