Nextcloud Notes MCP Server
Enables LLMs to manage and manipulate notes in Nextcloud Notes via WebDAV, supporting tasks like organizing, summarizing, rewriting, and translating notes through natural language commands.
README
Nextcloud Notes MCP Server
Nextcloud Notes MCP Server is a MCP server for the Nextcloud Notes app that lets a Large Language Model (LLM) do the heavy lifting for your notes.
Simply tell the LLM what to do with your notes — organize, summarize, rewrite, or perform any custom task — and it will execute your instructions automatically.
Features
- 💻 Fully Local Possible – Run the MCP Server and LLM models entirely on your own PC; no cloud needed.
- 🤖 LLM-Powered Note Management – Automate tasks like summarization, categorization, rewriting, or translations.
- 🌐 Nextcloud Integration via WebDAV – Access your notes directly through Nextcloud using the WebDAV protocol.
- ⚡ Boost Productivity – Save time by letting the LLM handle repetitive or complex note tasks.
Installation
-
Download the repository:
git clone https://github.com/rncz/nextcloud-notes-mcp-server.git -
Configure environment:
-
Change into the project directory:
cd nextcloud-notes-mcp-server -
Copy the sample environment file and edit credentials:
cp env_sample .env -
Open
.envand enter your Nextcloud WebDAV URL, username, and password.
-
-
Set up the Python environment and install the package:
uv venv uv tool install -e . -
Add MCP server to your LLM software (example for LM Studio): Edit your MCP JSON configuration:
{ "mcpServers": { "nextcloud-notes-mcp": { "command": "uvx", "args": [ "nextcloud-notes-mcp" ] } } } -
Test your setup:
- Use a model with tool calling enabled.
- Ask the model to access your notes and verify if the login is successful.
Good luck playing around with your Nextcloud Notes!
Description of MCP Tool Calls
check_webdav_login
Checks whether the WebDAV connection to Nextcloud is working. Returns a message indicating if authentication succeeded or failed.
ensure_notes_folder_exists
Ensures the /Notes folder exists in the user's Nextcloud WebDAV storage.
If it doesn’t exist, it is created.
Always returns a confirmation message.
list_uncategorized_notes
Lists all Markdown (.md) files located directly inside /Notes, excluding all subfolders.
Returns a list of filenames.
list_categories
Lists all subfolders inside /Notes.
Returns a list of category names (directories only, excluding .md files).
list_notes_of_a_category
Lists all Markdown (.md) files inside a specific category folder under /Notes.
Args:
category_name: Name of the folder inside/Notes.
Returns a list of note filenames, or an error message if the folder cannot be accessed.
read_note
Reads the contents of a Markdown note stored in Nextcloud via WebDAV.
Args:
filename: The name of the file, e.g.,note.md.category(optional): Subfolder under/Notes. If omitted, reads from root.
Returns the full text content of the note.
edit_note
Replaces the entire content of an existing Markdown note.
Args:
filename: Name of the note to edit.new_content: Full new content to overwrite the note with.category(optional): Folder under/Notes.
Returns a confirmation message.
create_note
Creates a new Markdown note.
Args:
filename: File name to create (must include.md).content: Initial content for the new note.category(optional): Folder under/Notes. Created automatically if missing.
Returns the WebDAV path of the created note.
delete_note
Deletes an existing Markdown note.
Args:
filename: File name to delete.category(optional): Folder under/Notes.
Returns a success message or an error.
rename_note
Renames a note inside /Notes or a category.
Args:
filename: Current name.new_filename: New name.category(optional): Folder under/Notes.
Returns the before → after path.
create_category
Creates a new category (a subfolder) inside /Notes.
Args:
category_name: The folder name to create.
Returns a success message.
edit_category
Renames an existing category inside /Notes.
Args:
old_name: Current category name.new_name: New category name.
Returns a success message or error.
delete_category
Deletes a category folder, including all notes inside it.
Args:
category_name: Folder name under/Notes.
Returns a success or error message.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。