Twitch Smithery
Connects AI systems to Twitch streams for real-time chat moderation, stream management, and viewer interaction through polls and predictions.
Integrates with Twitch's IRC and Helix API to provide real-time chat moderation with smart user targeting, automated timeout management, and stream control features including polls, predictions, and content updates.
What it does
- Send messages to Twitch chat
- Create polls and predictions for viewers
- Moderate chat with timeouts and bans
- Generate clips from stream moments
- Update stream title and category
- Analyze chat for trends and topics
Best for
About Twitch Smithery
Twitch Smithery is a community-built MCP server published by eclipse-xv that provides AI assistants with tools and capabilities via the Model Context Protocol. Twitch Smithery is a twitch stream manager for chat moderation, smart timeouts, and stream controls like polls, predicti It is categorized under communication, other.
How to install
You can install Twitch Smithery in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
License
Twitch Smithery is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Twitch MCP Server
A comprehensive Twitch MCP (Model Context Protocol) server providing chat moderation, stream management, and Twitch API integration for AI systems.
For Streamers
- Use this server via Smithery → Cursor (no local install needed)
- Quick setup guide: video-guide/final-setup-guide.md
- Smithery server page (Playground + one‑click add to Cursor): https://smithery.ai/server/@Eclipse-XV/twitch-mcp-smithery
- Recommended first tests:
- "Send a message to chat: Hello from MCP!"
- "Create a poll titled 'Which map?' with choices 'A, B' for 60 seconds"
Note: Actions run as your broadcaster account. Test in Smithery Playground first, then use the Connect section to one‑click add to Cursor and approve.
Overview
This MCP server allows AI agents to interact with Twitch streams through a standardized set of tools. It supports:
- Sending messages to chat
- Creating polls and predictions
- Generating clips
- Analyzing chat for trends and topics
- Moderating chat (timeout/ban users)
- Updating stream title and category
Getting Started
Prerequisites
- Node.js 18+ installed
- Twitch API credentials (Client ID and OAuth token)
- Twitch channel with appropriate permissions
Installation
- Clone this repository
- Install dependencies:
npm install
Configuration
You need to provide Twitch API credentials when connecting to the server. The following configuration options are required:
| Parameter | Description |
|---|---|
twitchClientId | Your Twitch application client ID |
twitchAuthToken | OAuth token (without 'oauth:' prefix) |
twitchBroadcasterId | Your Twitch user ID |
twitchChannel | Your Twitch channel name |
Deployment on Smithery
This server is configured for easy deployment on Smithery.
- Push this repository to GitHub
- Connect your GitHub account to Smithery
- Create a new deployment, selecting this repository
- Configure your Twitch API credentials in the Smithery dashboard
Available Tools
Chat Interaction
- sendMessageToChat: Send a message to Twitch chat
- getRecentChatLog: Get the last 20 chat messages for context
- analyzeChat: Analyze chat for topics and activity
Stream Management
- createTwitchPoll: Create a poll with multiple choices
- createTwitchPrediction: Create a prediction with outcomes
- createTwitchClip: Create a clip of the current stream
- updateStreamTitle: Change the stream title
- updateStreamCategory: Change the game/category
Moderation
- timeoutUser: Timeout a user for a specified duration
- banUser: Permanently ban a user from chat
Advanced Features
Smart User Resolution
When performing moderation actions, you can provide either:
- An exact username
- A behavioral descriptor (e.g., "toxic", "spam")
- A partial username match
The server will attempt to resolve the appropriate user based on chat history.
Intelligent Timeout Duration
The timeout tool automatically suggests an appropriate duration based on the severity of the provided reason:
- Spam/excessive emotes: 5 minutes
- Toxic behavior: 30 minutes
- Severe violations: 60 minutes
- Other violations: 10 minutes (default)
Known Issues & Limitations
Image Description Support
While AI assistants (like Cursor/Claude) can process and describe images, there are some considerations when using this with the Twitch MCP server:
- Image processing: Image analysis is handled by the AI client, not the MCP server itself
- Message length: AI-generated descriptions can be quite long. Twitch chat has a 500 character limit per message
- Auto-truncation: The
sendMessageToChattool now automatically truncates messages that exceed 500 characters and notifies you when this happens - Workaround: For detailed image descriptions, consider asking the AI to provide a shorter summary suitable for chat
Other Considerations
- API Rate Limits: Twitch API has rate limits that may affect rapid successive calls
- Permissions: Ensure your Twitch token has the necessary scopes for all desired features
- Stream Status: Some tools (like creating clips) require an active stream
License
ISC
Credits
Based on the original Java implementation of Twitch-MCP.
Alternatives
Related Skills
Browse all skillsPython library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.
Effective communication strategies for AI-assisted development. Learn context-first prompting, phased interactions, iterative refinement, and validation techniques to get better results from Claude and other AI coding assistants.
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks