Ulysses MCP
U

Ulysses MCP

An MCP server that enables AI assistants to interact with the Ulysses writing app on macOS through the x - callback - url API, providing functions such as document creation, content management, navigation, and metadata operations.
2.5 points
4.9K

What is Ulysses MCP Server?

Ulysses MCP Server is a bridge connecting AI assistants and the Ulysses writing app. It allows you to directly control Ulysses through AI assistants (such as Claude, Cline, etc.) to achieve automated writing and management. For example, you can ask the AI to create a diary, organize documents, add tags, and even read existing content for analysis. All operations are completed on your local computer, and data is not sent to the cloud (unless you use cloud-based AI services).

How to use Ulysses MCP Server?

The usage is divided into three simple steps: 1) Install Node.js and Ulysses MCP Server; 2) Configure your AI client (such as Claude Desktop or Cline) to connect to this server; 3) Use natural language commands in the AI assistant to control Ulysses. For example, you can say 'Help me create today's diary in the diary folder', and the AI will automatically complete it in Ulysses.

Use cases

This tool is particularly suitable for: content creators and bloggers (automatically generate and organize articles), students and researchers (manage notes and literature), diary enthusiasts (automatically create daily records), and anyone who wants to improve writing efficiency with AI.

Main features

๐Ÿ“ Create and manage documents
Automatically create new writing pages (Sheets) and support Markdown format. You can specify to save them in a specific folder (Group).
๐Ÿ“ Organize folder structure
Create new folders (Groups) to classify and manage your documents and build a clear writing project structure.
โœ๏ธ Edit and add content
Insert or append text in existing documents to facilitate the AI to help you continue writing or modify articles.
๐Ÿท๏ธ Add metadata
Attach notes, keywords (tags), and even pictures (in Base64 format) to documents to make document management more intelligent.
๐Ÿ“– Read document content
(Authorization required) Securely read the content and basic information of documents in Ulysses for the AI to analyze or summarize.
๐Ÿงญ Quick navigation
Quickly open specified documents or folders in Ulysses, or jump to specific views such as 'All', 'Last 7 days', 'Favorites'.
๐Ÿ”ง Advanced management
(Authorization required) Move, copy, rename, or delete documents or folders to completely manage your writing library.
๐Ÿ‘ Advantages
Completely local operation: All interactions with Ulysses occur on your Mac computer, ensuring privacy.
Seamless AI integration: Use natural language commands to let AI assistants manage your writing and improve efficiency.
Comprehensive functions: Cover common document operations from creation, editing, organization to reading.
Safe and controllable: Destructive operations (such as deletion) have rate limits, and critical operations require your explicit authorization.
โš ๏ธ Limitations
Only available on macOS: Ulysses is a Mac/iOS app, so this tool can only be used on macOS.
Dependent on the Ulysses API: The functions are limited by the 'x-callback-url' interface provided by the Ulysses official, and not all operations within the software can be implemented (such as search, statistics, export).
Manual authorization required: Advanced functions such as reading content require you to manually approve once in Ulysses.
Configuration required: Simple configuration is required in the AI client to use.

How to use

Installation prerequisites
Ensure that your computer has the following installed: 1) macOS system; 2) Ulysses app; 3) Node.js (version 18 or higher).
Install the MCP server
Open the Terminal and run the following command to install Ulysses MCP Server.
Build the auxiliary application (a crucial step)
To handle Ulysses callbacks (such as authorization confirmation), you need to build a local auxiliary application. Run the following in the Terminal:
Configure your AI client
According to the AI client you are using (such as Claude Desktop or Cline), edit its configuration file and add Ulysses MCP Server. The following is a configuration example for Claude Desktop.
Start using
Restart your AI client. Now, you can let the AI assistant use Ulysses in the conversation! For example: 'Help me create a new page in the 'Diary' folder.'

Usage examples

Example 1: Create a daily diary
Every morning, let the AI assistant automatically create a well - formatted diary in Ulysses.
Example 2: Organize blog drafts
After writing a batch of blog drafts, let the AI add tags to them uniformly.
Example 3: AI - assisted continuation and modification
When you get stuck in writing, you can let the AI read the existing content and provide suggestions for continuation or direct modification.

Frequently Asked Questions

Will my writing content be uploaded to the Internet?
Why is 'authorization' required? Is the authorization token secure?
How can I get the ID of a page or folder in Ulysses?
Is this tool developed by the Ulysses official?
What should I do if the AI client cannot connect to the server after installation?

Related resources

Project code repository and latest version
View the source code, report issues, or contribute code on GitHub.
Model Context Protocol (MCP) official website
Understand the detailed specifications and design concepts of the MCP protocol.
Ulysses x - callback - url API documentation
The automation interface documentation provided by the Ulysses official, listing all available operation commands.
Accompanying blog post: From frustration to a smarter workflow
Understand the original intention and thought process of developing this tool.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "ulysses": {
      "command": "node",
      "args": ["/path/to/ulysses-mcp/build/index.js"]
    }
  }
}

{
  "mcpServers": {
    "ulysses": {
      "disabled": false,
      "autoApprove": [],
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/ulysses-mcp/build/index.js"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

C
Cipher
Cipher is an open-source memory layer framework designed for programming AI agents. It integrates with various IDEs and AI coding assistants through the MCP protocol, providing core functions such as automatic memory generation, team memory sharing, and dual-system memory management.
TypeScript
0
5 points
A
Apple Notes MCP
A server that provides local Apple Notes database access for the Claude desktop client, supporting reading and searching of note content.
Python
13.3K
4.3 points
M
MCP Server Weread
The WeRead MCP Server is a lightweight service that bridges WeRead data and AI clients, enabling in - depth interaction between reading notes and AI.
TypeScript
13.2K
4 points
M
MCP Notion Server
Certified
The Notion MCP Server is a middleware service that connects the Notion API with the LLM, optimizing interaction efficiency through Markdown conversion.
TypeScript
15.2K
5 points
M
MCP Obsidian
This project is an MCP server used to interact with the Obsidian note application through the Local REST API plugin of Obsidian. It provides various tools to operate and manage files in Obsidian, including listing files, retrieving file content, searching, modifying content, and deleting files.
Python
16.2K
5 points
M
MCP Atlassian
MCP Atlassian is a Model Context Protocol server designed for Atlassian products (Confluence and Jira), supporting both cloud and on-premises deployments and providing AI assistant integration functions.
Python
14.3K
5 points
M
MCP Logseq Server
An MCP server for interacting with the LogSeq note-taking app, providing various API tools to operate on note content.
Python
17.2K
4.1 points
S
Solana Docs MCP Server
A TypeScript-based MCP server that implements a simple note system and supports note creation and summarization functions
TypeScript
12.9K
4.2 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.5K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
28.6K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
17.5K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
53.9K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
51.3K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
24.3K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
17.2K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
75.7K
4.7 points