About Twitch MCP Server
Twitch MCP Server exposes Twitch Helix data through tools for clients that need channel, stream, game, and related information. It also retrieves clips, videos, chat details, emotes, badges, and archived-video comments.
Key features
- 01Channel and user profiles
- 02Stream and live-stream details
- 03Game and category search
- 04Clips, videos, and comments
- 05Emotes, badges, and chat settings
Use cases
- 01Inspect a channel or user profile
- 02Find live streams by game or language
- 03Retrieve channel clips and videos
- 04Review archived-video comments
MCP support
Exposes Twitch API capabilities as tools for MCP clients, using the Helix API and GraphQL for archived-video comments.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMETwitch MCP Server
A Model Context Protocol (MCP) server that interacts with the Twitch API. This server utilizes the Twitch Helix API to retrieve channel information, stream details, game data, and more.
Features
- Get channel information (profile, description, creation date, etc.)
- Get stream information (title, game, viewer count, start time, etc.)
- Get list of top games
- Search categories/games
- Search channels
- Get live streams (filterable by game and language)
- Get global emotes
- Get global chat badges
- Get user information
- Get clips from a channel
- Get chat settings
- Get videos from a specified channel
- Get comments from archived videos (using GraphQL API)
Prerequisites
- Node.js (v18 or higher recommended)
- Twitch Developer Account
- Twitch API Client ID and Client Secret
- Twitch GraphQL Client ID (for video comments feature)
Installation
Install the package using npm:
npm install @mtane0412/twitch-mcp-server
Configuration
-
Create a new application in the Twitch Developer Console
-
Set the following environment variables:
# macOS/Linux
export TWITCH_CLIENT_ID="your_client_id"
export TWITCH_CLIENT_SECRET="your_client_secret"
# Windows (PowerShell)
$env:TWITCH_CLIENT_ID="your_client_id"
$env:TWITCH_CLIENT_SECRET="your_client_secret"
Alternatively, you can create a .env file:
TWITCH_CLIENT_ID=your_client_id
TWITCH_CLIENT_SECRET=your_client_secret
Usage
After installation, you can start using the server by running:
npx @mtane0412/twitch-mcp-server
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspect
The Inspector will provide a URL to access debugging tools in your browser.
License
MIT License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.