
Twitch Chat and Stream Management Server
@Eclipse-XV
About Twitch Chat and Stream Management Server
Enable AI agents to interact with Twitch streams by sending chat messages, managing polls and predictions, creating clips, analyzing chat activity, and moderating users. Automate stream title and category updates while leveraging intelligent user resolution and timeout duration s
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"twitch-mcp-smithery": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"@smithery/cli@latest",
"run",
"@Eclipse-XV/twitch-mcp-smithery",
"--key",
"YOURKEYHERE",
"--profile",
"YOURPROFILEHERE"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Twitch Chat and Stream Management Server?
It is an MCP server that provides AI-powered tools for Twitch streamers, allowing coding and chat assistants (such as Qwen Code, LM Studio, or Claude) to interface with Twitch chat for moderation, stream management, and engagement.
How to use Twitch Chat and Stream Management Server?
Install Node.js 14+ and Java 11+. Create a config file at the correct OS‑specific path with your Twitch channel name, bare access token, client ID, and broadcaster ID. Then configure your MCP client (e.g., Qwen Code) to use the stdio transport with the command npx -y twitch-mcp-server@latest --config <path>. When using Qwen Code, the server launches automatically; manual startup is not needed.
Key features of Twitch Chat and Stream Management Server
- Send and read messages; view recent chat logs and perform chat analysis
- Timeout or ban users by username or descriptor
- Update stream title and category; create clips
- Create and manage polls and predictions
Use cases of Twitch Chat and Stream Management Server
- Automate chat moderation using an AI coding assistant
- Change stream title or category without leaving your editor
- Engage viewers by launching polls or predictions through chat commands
- Retrieve recent chat logs for community analysis or record keeping
FAQ from Twitch Chat and Stream Management Server
How do I fix authentication failures?
Ensure the auth value is a bare access token (no "oauth:" prefix), verify that your clientId and scopes match the token, and confirm that broadcasterId matches your channel.
Why does npx prompt in headless environments?
The recommended Qwen configuration includes the -y flag so that npx runs non‑interactively. Make sure that flag is present in your command arguments.
Can multiple clients connect at the same time?
No. Only one client (e.g., Qwen Code) should be connected to the server at a time.
What are the system requirements?
Node.js 14+ and Java 11+ must be on the system PATH. They should be installed on the same OS where Qwen runs (on Windows, not under WSL).
Where should the config file be placed?
On Windows: C:/Users/<you>/AppData/Roaming/twitch-mcp/config.json; on macOS: `~/Library/Application
Frequently asked questions
How do I fix authentication failures?
Ensure the `auth` value is a bare access token (no "oauth:" prefix), verify that your `clientId` and scopes match the token, and confirm that `broadcasterId` matches your channel.
Why does npx prompt in headless environments?
The recommended Qwen configuration includes the `-y` flag so that npx runs non‑interactively. Make sure that flag is present in your command arguments.
Can multiple clients connect at the same time?
No. Only one client (e.g., Qwen Code) should be connected to the server at a time.
What are the system requirements?
Node.js 14+ and Java 11+ must be on the system PATH. They should be installed on the same OS where Qwen runs (on Windows, not under WSL).
Where should the config file be placed?
On Windows: `C:/Users/<you>/AppData/Roaming/twitch-mcp/config.json`; on macOS: `~/Library/Application
Basic information
More AI & Agents MCP servers
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
Comments