streamlabs-mcp

streamlabs-mcp

MCP server that gives AI assistants direct control over Streamlabs Desktop, enabling scene switching, source/audio management, and streaming/recording controls through natural language.

Category
访问服务器

README

streamlabs-mcp

An MCP (Model Context Protocol) server that gives AI assistants direct control over Streamlabs Desktop — switch scenes, show/hide sources, adjust audio, start/stop streaming or recording, manage studio mode, and more.

It talks to Streamlabs Desktop's own local Remote Control API (the same one used by Streamlabs' official mobile remote-control app), so no unofficial hacks or screen automation are involved.

This is not a Claude-only tool. MCP is an open, model-agnostic protocol, so this server works with any MCP-compatible client — Claude Desktop, Claude Code, Cursor, or anything else that can spawn a local stdio MCP server.

Disclaimer: This is an independent, community project. It is not made or endorsed by Streamlabs. Use at your own risk — some tools (e.g. streamlabs_toggle_streaming) can start/stop your live stream, so give your AI assistant clear instructions about when it's allowed to use them.

Features

  • 59 tools covering scenes, scene items (position/scale/rotation/crop), sources, audio, streaming/recording, replay buffer, studio mode, scene collections, notifications, and performance stats.
  • Pure stdio MCP server — no cloud relay, no external service. Your assistant talks directly to Streamlabs Desktop over your own machine's loopback connection.
  • Zero configuration beyond a single token.

Prerequisites

  • Streamlabs Desktop installed and running on the same machine.
  • Node.js 18 or newer.
  • An MCP-compatible client (Claude Desktop, Claude Code, Cursor, etc.).

1. Enable Remote Control in Streamlabs Desktop

  1. Open Streamlabs Desktop.
  2. Go to Settings -> Remote Control.
  3. Click the QR code, then Show details.
  4. Copy the token shown there. Treat this like a password — anyone with it can control your stream.

2. Install

git clone https://github.com/AhmadTariq1337/streamlabs-mcp.git
cd streamlabs-mcp
npm install

3. Configure your MCP client

This server reads two environment variables:

Variable Required Default Description
STREAMLABS_TOKEN Yes — The token from step 1.
STREAMLABS_HOST No 127.0.0.1:59650 Host:port of the Streamlabs Desktop API.

Point your MCP client at node <path-to-this-folder>/index.js with STREAMLABS_TOKEN set. Examples below.

Claude Desktop / Claude Code

Add to your MCP config (Claude Desktop: Settings -> Developer -> Edit Config; Claude Code: your project or user mcp.json):

{
  "mcpServers": {
    "streamlabs": {
      "command": "node",
      "args": ["/absolute/path/to/streamlabs-mcp/index.js"],
      "env": {
        "STREAMLABS_TOKEN": "paste-your-token-here"
      }
    }
  }
}

Restart your client afterward.

Cursor

Same shape, in Cursor's mcp.json:

{
  "mcpServers": {
    "streamlabs": {
      "command": "node",
      "args": ["/absolute/path/to/streamlabs-mcp/index.js"],
      "env": {
        "STREAMLABS_TOKEN": "paste-your-token-here"
      }
    }
  }
}

Any other MCP client

This is a standard stdio MCP server — configure your client to run:

node /absolute/path/to/streamlabs-mcp/index.js

with STREAMLABS_TOKEN (and optionally STREAMLABS_HOST) set in its environment. That's all any MCP client needs.

4. Test it

With Streamlabs Desktop running, ask your assistant something like "list my Streamlabs scenes" or "what's my current streaming status?".

Tool reference

Scenes

Tool Description
streamlabs_list_scenes List all scenes in the current scene collection.
streamlabs_get_scene Get a specific scene by id.
streamlabs_get_active_scene Get the currently active scene and its items.
streamlabs_switch_scene Switch to a different scene.
streamlabs_create_scene Create a new empty scene.
streamlabs_remove_scene Delete a scene.
streamlabs_rename_scene Rename a scene.
streamlabs_clear_scene Remove all items from a scene.
streamlabs_add_source_to_scene Add an existing source to a scene.
streamlabs_create_and_add_source Create a new source and add it to a scene in one step.

Scene items

Tool Description
streamlabs_set_scene_item_visibility Show or hide a scene item.
streamlabs_remove_scene_item Remove an item from a scene.
streamlabs_set_scene_item_transform Set position/scale/rotation/crop.
streamlabs_set_scene_item_scale Set scale around an origin point.
streamlabs_reset_scene_item_transform Reset transform to default.
streamlabs_flip_scene_item_x / _y Flip an item horizontally/vertically.
streamlabs_rotate_scene_item Rotate by a number of degrees.
streamlabs_center_scene_item Center an item on the canvas.
streamlabs_fit_scene_item_to_screen Fit to canvas, preserving aspect ratio.
streamlabs_stretch_scene_item_to_screen Stretch to fill the canvas.

Sources

Tool Description
streamlabs_list_sources List all sources.
streamlabs_get_source Get a source by id.
streamlabs_get_sources_by_name Find sources by display name.
streamlabs_create_source Create a source without adding it to a scene.
streamlabs_remove_source Delete a source everywhere it's used.
streamlabs_list_available_source_types List source types this system can create.
streamlabs_get_source_settings Get a source's settings.
streamlabs_update_source_settings Update a source's settings (URL, text, etc).
streamlabs_rename_source Rename a source.
streamlabs_duplicate_source Duplicate a source.
streamlabs_refresh_source Reload a source (e.g. a browser source).

Audio

Tool Description
streamlabs_list_audio_sources Audio sources for the current scene.
streamlabs_list_all_audio_sources Every audio source, all scenes.
streamlabs_list_audio_sources_for_scene Audio sources for a given scene.
streamlabs_set_source_muted Mute/unmute an audio source.
streamlabs_set_source_volume Set volume (0.0–1.0).

Streaming / recording

Tool Description
streamlabs_get_streaming_status Current streaming/recording state.
streamlabs_toggle_streaming Start/stop the live stream.
streamlabs_toggle_recording Start/stop local recording.
streamlabs_start_replay_buffer / streamlabs_stop_replay_buffer Control the replay buffer.
streamlabs_save_replay Save the current instant replay.

Studio mode

Tool Description
streamlabs_get_studio_mode_status Current studio mode state.
streamlabs_enable_studio_mode / streamlabs_disable_studio_mode Toggle studio mode.
streamlabs_execute_studio_mode_transition Push the previewed scene live.

Scene collections

Tool Description
streamlabs_list_scene_collections List saved scene collections.
streamlabs_get_active_scene_collection Currently loaded collection.
streamlabs_load_scene_collection Switch collections.
streamlabs_create_scene_collection Create a new collection.
streamlabs_delete_scene_collection Delete a collection.
streamlabs_rename_scene_collection Rename a collection.

Notifications & performance

Tool Description
streamlabs_list_notifications List in-app notifications.
streamlabs_mark_notification_read / streamlabs_mark_all_notifications_read Mark notifications read.
streamlabs_push_notification Push a new notification.
streamlabs_show_notifications_panel Open the notifications panel.
streamlabs_get_performance_stats CPU, FPS, dropped frames, bandwidth, disk space.

Troubleshooting

  • Connection times out: Streamlabs Desktop must be running with Remote Control enabled (step 1). Check that Windows Firewall isn't blocking Node from opening a local connection to the port.
  • Auth error: the token may have been regenerated since you copied it — grab the current one from Settings -> Remote Control.
  • Different port: set STREAMLABS_HOST if your Streamlabs Desktop build listens elsewhere, e.g. "127.0.0.1:PORT".
  • A specific tool errors on a newer Streamlabs Desktop version: the underlying API is Streamlabs' internal service layer and isn't a versioned public contract, so a method name can occasionally change between releases. Open an issue with the error message, or send a PR.

Security note

STREAMLABS_TOKEN grants full remote control of your stream (including going live). Keep it out of version control — .gitignore already excludes .env. Use .env.example as a template.

Contributing

Issues and PRs welcome. If you add a tool, please also add it to the reference table above.

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选