Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@streamelements-mcp Update !discord to reply 'Join us: discord.gg/pixelpals' and set a 30-second cooldown."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Yes, Claude, ChatGPT and other AI agents can work in your StreamElements account. StreamElements has an AI chatbot variable, $(ai), but it runs inside your stream chat, not as an app in ChatGPT or Claude. Cotlet.dev connects your own signed-in StreamElements account to any AI agent, so you can ask in plain words and the AI lists and edits your chat commands for you.
List all my StreamElements chat commands with their cooldown and user level, sorted by name.
Change the !discord command to reply "Join the crew: discord.gg/pixelpals" and set the cooldown to 30 seconds.
Update !schedule to say I stream Monday, Wednesday and Friday at 7 pm CET.
Which of my commands are disabled? Turn !giveaway and !merch back on.
Rename !socials to !links and add my new TikTok handle @pixelpals to the reply.
Related MCP server: Minecraft Command Execution MCP Server
Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.
Copy .cursor/mcp.json from this repo into your project:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}This repo is a real MCP server. It speaks MCP over stdio, lists its StreamElements tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.
{"mcpServers":{"streamelements":{"command":"uvx","args":["streamelements-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}Or with Docker:
docker build -t streamelements-mcp .
docker run -i --rm -e COTLET_API_KEY streamelements-mcpTools: streamelements_guide, streamelements_status, streamelements_open, streamelements_read, streamelements_click, streamelements_type, streamelements_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".
Python 3.10+, nothing else to install. From PyPI:
pip install streamelements-mcp # or run it once: uvx streamelements-mcp connect
streamelements-mcp connectOr straight from this repo:
export COTLET_API_KEY="your-key"
python3 streamelements_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 streamelements_agent.py status # is StreamElements ready in your Cotlet.dev account
python3 streamelements_agent.py guide # StreamElements screens and sign-in link
python3 streamelements_agent.py read # open StreamElements, read the page, close the browser
python3 streamelements_agent.py tools # list Cotlet.dev tools
python3 streamelements_agent.py serve # start the stdio MCP server (same as no argument)Is there StreamElements API documentation I need to use first?
You don't need to work with any StreamElements API. Cotlet.dev works in your own signed-in StreamElements account, so your AI agent can list and edit chat commands without code, tokens or API setup.
How do I connect StreamElements to ChatGPT?
Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to StreamElements once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no StreamElements API key.
Is there a way to use Claude with StreamElements?
Yes. In Claude Code run the one-line claude mcp add command above; in the Claude app add https://cotlet.dev/mcp/v1 as a custom connector. Claude then works in your own StreamElements account.
Is there a StreamElements MCP server?
Cotlet.dev is a hosted MCP server that works in StreamElements for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.
Does StreamElements have a ChatGPT chatbot built in?
StreamElements has an AI chatbot variable, $(ai) (alias $(chatgpt)), that answers viewers inside your stream chat. To have ChatGPT or Claude manage your StreamElements commands for you, connect them with Cotlet.dev.
Start free: https://cotlet.dev/signup?app=streamelements&utm_source=github&utm_medium=readme&utm_campaign=streamelements
Click a numbered element on the current StreamElements page.
Inputs: element (required).
Close the StreamElements browser session when the work is done, so credits stop running.
Inputs: no named parameters.
How to work in StreamElements (list and edit chat commands): its screens and the sign-in link. Call this first.
Inputs: task.
Open a StreamElements page in your signed-in Cloud Browser (default https://streamelements.com) to work with list and edit chat commands.
Inputs: url.
Read the current StreamElements page: its text and numbered buttons, links and fields.
Inputs: element.
Check that your Cotlet.dev account and StreamElements are ready: account, credits and StreamElements connection.
Inputs: no named parameters.
Type text into a numbered field on the current StreamElements page.
Inputs: text (required), element (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool maps to a distinct browser-automation action: open, read, click, type, close, plus guide and status. The boundaries between guide (instructions) and status (readiness check) are clear enough, though both are meta-tools that could initially be confused. Open versus read is also distinguishable because one navigates and the other extracts content.
All tools follow the same streamelements_<verb> snake_case pattern. The prefix is consistent and the verbs are simple and readable. There is no mixing of camelCase or conflicting conventions.
Seven tools is a well-scoped set for a browser-automation workflow focused on StreamElements chat-command management. Each tool has a clear role, and none appears redundant or purely decorative.
The surface covers the core lifecycle: sign-in guidance, readiness check, opening a page, reading it, interacting via click and type, and closing the session. Minor gaps exist around navigation history or waiting for dynamic updates, but the essential list-and-edit workflow is covered.
Query your Twitch streams, events, supporters, raids & rankings from an AI assistant via OAuth.
Manage your Twitch raid-train schedule from an AI assistant: claim, release & trade slots via OAuth.
Manage ElevenLabs voice agents and generate speech, music, sound effects, images, and video.
Build, edit and place TikTok LIVE overlay widgets (alerts, goals, games) from your AI assistant.