모델 Context Protocol (MCP) 서버는 Joplin Note-taking 앱입니다.

belsar.ai에 의해 설계하여 설치 및 사용하기 쉬운.

비디오

https://www.youtube.com/watch?v=B3qJa7ycqNM&t=6s] [T0]] [T0]] [T0]] [T0]] [T0]] [T0]] [T0]] [T0] [T0] [T0]] [T0] [T0] [T0]] [T0]] [T0] [T0] [T0] [T0] [T0]] [T0] [T0]] [T0] [T0] [T0]] [T0]] [T0] [T0] [T0]] https://www.youtube.com/watch?v=B3qJa7ycqNM&t=6s] https://www.youtube.com/watch?v=B3qJa7ycqNM&t=6s]]] https://www.youtube.com/watch?v=B3qJa7ycqNM&t=6s]]]]]] [[https://www.youtube.com/watch?v=B3qJa7ycqNM&t=6s]]]]]]] [[[[[[https://www.youtube.com/watch?v=B3qJa7ycqNM&t=6s]]]]]]]]]]]]]] [[[[[[[https://www.youtube.com/watch?v=B3qJa7ycqNM&t=6s]]]]]]]]]]]]]]]]]] [[[[[[[[[[[[[[[[[[[[[[

플랫폼 지원

macOS 및 Linux에서 사용할 수 있습니다. Windows 사용자는 WSL2를 사용해야 합니다.

건축

기본적으로, 이 MCP 서버는 두 가지 도구를 노출:

• execute_joplin_readonly_script: 읽기 전용 모드에서 실행 스크립트 (inspecting/reading notes and Notebook).
• execute_joplin_script: 수정, 생성 또는 삭제를 수행 할 수있는 실행 스크립트.

이 스크립트 기반 실행 패턴은 MCP 서버에 대한 Anthropic의 권장 패턴을 따르며, MCP 서버를 오늘 빌드하는 가장 뛰어난 방법입니다.

Scripts는 Anthropic Sandbox Runtime의 OS 레벨에 격리된 별도의 런너 프로세스에서 실행됩니다. node:vm]는 프로세스 내에서 사용할 수 있는 글로벌을 제한합니다. Sandbox Runtime은 네트워크 액세스 및 파일 시스템 쓰기를 차단하는 보안 경계입니다.

runner는 joplin.*] 메소드를 Joplin에 직접 얘기하지만, 모든 요청은 브로커를 통과하여 API 메소드의 특정 세트를 허용한다.

joplin-mcp

Model Context Protocol (MCP) server for the Joplin note-taking app.

Designed by belsar.ai to be easy to install & enjoyable to use.

Video

https://www.youtube.com/watch?v=B3qJa7ycqNM&t=6s

Platform Support

Available on macOS and Linux. Windows users should use WSL2.

Architecture

By default, this MCP server exposes two tools:

• execute_joplin_readonly_script: For running scripts in read-only mode (inspecting/reading notes and notebooks).
• execute_joplin_script: For running scripts that can also perform modifications, creations, or deletions.

This script-based execution pattern follows Anthropic’s recommended pattern for MCP servers and is the most performant, token-efficient way to build an MCP server today.

Scripts execute in a separate runner process isolated at the OS level by Anthropic Sandbox Runtime. node:vm limits the globals available inside that process; the Sandbox Runtime is the security boundary that blocks network access and filesystem writes.

joplin api ←http→ broker (allowlisted proxy) ←stdio→ runner (sandboxed)

The runner calls joplin.* methods as if talking to Joplin directly, but all requests pass through the broker, which only permits a specific set of API methods. The broker is the only piece that can interact with your notes — and nothing else.

Quick Start

1. Open Joplin & navigate to tools > web clipper > enable web clipper service
2. The Joplin app needs to remain running (minimized is fine)
3. Add the server to your MCP client:

Claude Code:

claude mcp add --scope user --transport stdio joplin -- npx -y @belsar-ai/joplin-mcp

Codex:

codex mcp add joplin -- npx -y @belsar-ai/joplin-mcp

Agy: add this entry to ~/.gemini/config/mcp_config.json (or configure the same stdio server through /mcp):

{
  "mcpServers": {
    "joplin": {
      "command": "npx",
      "args": ["-y", "@belsar-ai/joplin-mcp"]
    }
  }
}

4. That’s it. Send a test request like “Find my notes about installing Fedora linux”.

Linux Requirements

Install the following system packages before first use:

# Fedora
sudo dnf install bubblewrap socat ripgrep

# Ubuntu/Debian
sudo apt install bubblewrap socat ripgrep

The server will fail with an error message if these are missing.

Uninstall

claude mcp remove joplin

codex mcp remove joplin

agy mcp remove joplin

Configuration (Optional)

Notebook Scope Config

Create .mcp-config/joplin-mcp.toml in your project root to scope which notebooks are visible:

[defaults]
notebook = "Notes"

[scope]
notebooks = ["Notes", "Software"]

• defaults.notebook: Where new notes go if you don’t specify a notebook
• scope.notebooks: Only these notebooks are visible to the AI