A Model Context Protocol (MCP) 서버는 OBS WebSocket API를 통해 OBS Studio를 제어할 수 있습니다.

개요

이 MCP 서버는 OBS Studio를 통해 프로그래밍 제어를 통해 AI 에이전트 (클래드와 같은)를 제공합니다. 자동화 된 장면 전환, 녹음 제어, 스트리밍 관리 및 자연 언어 상호 작용을 통해 더 많은.

특징

• 81 MCP 도구: 9개의 툴 그룹에서 OBS Studio 운영에 대한 종합 제어
• Scene 관리: 목록, 스위치, 생성 및 제거 OBS 장면
• Scene Presets: 저장 및 복원 소스 가시 구성 -Recording Control: 시작, 중지, 일시 중지, 재시작, 모니터링
• Streaming Control: 시작, 중지, 모니터링
• 소스 관리: 목록 및 제어 소스 가시성
• ** 오디오 제어 **: 입력 mute 및 볼륨 레벨 관리
• Screenshot Sources: 주기적 이미지 캡처와 AI 시각 모니터링
• Agentic Scene Design: 생성 및 조작 소스 (텍스트, 이미지, 색상, 브라우저, 미디어)
• **도움 & 디스커버리 **: 주제 기반 지도와 내장된 도움말 도구
• Status 모니터링: Query OBS 연결 및 작동 상태

agentic-obs

A Model Context Protocol (MCP) server that enables AI assistants to control OBS Studio through the OBS WebSocket API.

Overview

This MCP server provides AI agents (like Claude) with programmatic control over OBS Studio, enabling automated scene switching, recording control, streaming management, and more through natural language interactions.

Features

• 81 MCP Tools: Comprehensive control over OBS Studio operations in 9 tool groups
• Scene Management: List, switch, create, and remove OBS scenes
• Scene Presets: Save and restore source visibility configurations
• Recording Control: Start, stop, pause, resume, and monitor recording
• Streaming Control: Start, stop, and monitor streaming
• Source Management: List and control source visibility
• Audio Control: Manage input mute and volume levels
• Screenshot Sources: AI visual monitoring with periodic image capture
• Agentic Scene Design: Create and manipulate sources (text, image, color, browser, media)
• Help & Discovery: Built-in help tool with topic-based guidance
• Status Monitoring: Query OBS connection and operational status
• Automation Rules: Event-triggered actions and scheduled tasks for hands-free OBS control
• 4 MCP Resources: Scenes, screenshots, screenshot URLs, and presets exposed as resources
• 14 MCP Prompts: Pre-built workflows for common tasks and diagnostics
• MCP Completions: Autocomplete for prompt arguments and resource URIs
• Claude Skills: Shareable skill packages for advanced AI orchestration
• TUI Dashboard: Terminal interface for status, config, and history (--tui flag)
• Web Dashboard: Browser-based dashboard at http://localhost:8765/

Prerequisites

• Go 1.25.5+ - Download
• OBS Studio 28+ - Includes built-in WebSocket server
• Git - For version control

Installation

Option 1: Install with Go (Recommended)

go install github.com/ironystock/agentic-obs@latest

This installs the agentic-obs binary to your $GOPATH/bin directory.

Option 2: Build from Source

# Clone the repository
git clone https://github.com/ironystock/agentic-obs.git
cd agentic-obs

# Build with Make (recommended - includes version info)
make build

# Or build directly with Go
go build -o agentic-obs .

# Verify the build
./agentic-obs --version

For cross-platform builds, release automation, and advanced build options, see docs/BUILD.md.

Configure OBS Studio

1. Open OBS Studio
2. Go to Tools → WebSocket Server Settings
3. Enable the WebSocket server (default port: 4455)
4. Set a password (optional but recommended)
5. Note your connection details

Usage

Running the Server

# MCP server mode (default) - if installed via go install
agentic-obs

# TUI dashboard mode - terminal interface for monitoring
agentic-obs --tui
agentic-obs -t

# Or run directly from source
go run main.go