udemy-mcp
Connects an AI agent to your own signed-in Udemy instructor account so it can create and manage coupons (e.g. paid or free-enrollment codes with start dates and durations), edit course details such as titles and subtitles, and add lectures and upload videos to existing sections. Also exposes browser-style tools (guide, status, open, read, click, type, close) for navigating and inspecting Udemy screens in the hosted cloud browser.
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., "@udemy-mcp Make a free coupon for 100 students on my Excel course and send me the link."
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.
How to connect Udemy to Claude Code, ChatGPT and any AI agent
Yes, Claude, ChatGPT and other AI agents can work in your Udemy account. Udemy's official ChatGPT app helps you discover public courses, and the official Udemy Business connector for Claude needs an Enterprise subscription with the AI Connectors add-on. Cotlet.dev connects your own signed-in Udemy instructor account to any AI agent, so the AI creates coupons and updates your courses for you.
What you can ask
Create a coupon BLACKFRIDAY26 for my Python Bootcamp course at $12.99, starting November 27 and running for 5 days.
Make a free coupon for 100 students on my Excel for Beginners course and send me the link.
Change the title of my React course to "React 19 Complete Guide" and rewrite the subtitle to match.
Add a lecture called "Deploying to Vercel" at the end of section 8 in my Next.js course and upload this video.
Which of my coupons end this week? Create new ones at the same price for my top 3 courses.
Related MCP server: Game Studio MCP
Connect in 2 minutes
Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.
Claude Code
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"ChatGPT
Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.
Cursor
Copy .cursor/mcp.json from this repo into your project:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}Run it locally (stdio)
This repo is a real MCP server. It speaks MCP over stdio, lists its Udemy 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":{"udemy":{"command":"uvx","args":["udemy-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}Or with Docker:
docker build -t udemy-mcp .
docker run -i --rm -e COTLET_API_KEY udemy-mcpTools: udemy_guide, udemy_status, udemy_open, udemy_read, udemy_click, udemy_type, udemy_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".
Command line
Python 3.10+, nothing else to install. From PyPI:
pip install udemy-mcp # or run it once: uvx udemy-mcp connect
udemy-mcp connectOr straight from this repo:
export COTLET_API_KEY="your-key"
python3 udemy_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 udemy_agent.py status # is Udemy ready in your Cotlet.dev account
python3 udemy_agent.py guide # Udemy screens and sign-in link
python3 udemy_agent.py read # open Udemy, read the page, close the browser
python3 udemy_agent.py tools # list Cotlet.dev tools
python3 udemy_agent.py serve # start the stdio MCP server (same as no argument)Questions from Udemy users
Does Udemy have an API?
Udemy has an Instructor API that lists your courses, reads reviews, and reads and answers Q&A questions and direct messages (checked 12 Oct 2026). It has no coupons, announcements, review responses, course edits or revenue. Cotlet.dev works in your own signed-in Udemy account, so your AI agent can create coupons and update courses with no API key and no code.
How do I connect Udemy to ChatGPT?
Udemy's official ChatGPT app helps you discover public courses. To manage your own courses, add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to Udemy once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no Udemy API key.
Is there a way to use Claude with Udemy?
Yes. Claude lists an official Udemy Business connector, which needs an Enterprise subscription plus the AI Connectors add-on. To work in your own Udemy account, run the one-line claude mcp add command above in Claude Code, or add https://cotlet.dev/mcp/v1 as a custom connector in the Claude app.
Is there a Udemy MCP server?
Udemy offers an official Udemy Business connector for Claude, focused on learning. Cotlet.dev is a hosted MCP server that works in your own Udemy account for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.
Find it on
Also works with
Start free: https://cotlet.dev/signup?app=udemy&utm_source=github&utm_medium=readme&utm_campaign=udemy
Available Tools
7 toolsudemy_clickBInspect
Click a numbered element on the current Udemy page.
Inputs: element (required).
udemy_closeAInspect
Close the Udemy browser session when the work is done, so credits stop running.
Inputs: no named parameters.
udemy_guideAInspect
How to work in Udemy (create coupons and update courses): its screens and the sign-in link. Call this first.
Inputs: task.
udemy_openCInspect
Open a Udemy page in your signed-in Cloud Browser (default https://www.udemy.com) to work with create coupons and update courses.
Inputs: url.
udemy_readAInspect
Read the current Udemy page: its text and numbered buttons, links and fields.
Inputs: element.
udemy_statusAInspect
Check that your Cotlet.dev account and Udemy are ready: account, credits and Udemy connection.
Inputs: no named parameters.
udemy_typeCInspect
Type text into a numbered field on the current Udemy page.
Inputs: text (required), element (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a distinct role in a browser-automation workflow: setup/help (guide, status), session lifecycle (open, close), and page interaction (read, click, type). There is no meaningful overlap between tools, and the descriptions make the boundaries clear.
All tools consistently use the udemy_ prefix, which makes the set easy to recognize. Most names use clear action verbs, though guide and status are noun-like rather than verb-based, a minor deviation.
Seven tools is well-scoped for a browser-automation server focused on Udemy coupon creation and course updates. Each tool earns its place, with no obviously redundant or missing lifecycle pieces.
The set covers the essential browser workflow: check readiness, read page state, open pages, interact via click/type, and close the session. Some common browser actions like scrolling, navigation history, or waiting are absent, but the core loop is functional.
Maintenance
Related MCP Connectors
The official Upwork MCP server, letting AI agents connect to Upwork and act on your behalf.
The AI admin for Discord: manage channels, roles, members, moderation and automations.
Teachable MCP server for ChatGPT, Claude and any AI agent: update lecture, create coupon, send email, reply to comment and list enrollments in your own Teachable account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Teachable yourself; Cotlet does not store your password and you need no Teachable API key. About the official Teachable API: Teachable has a public API, but only on the Growth plan and up, and it reads courses and lecture content and manages users, enrollments, pricing plans and transactions (checked 11 Oct 2026). Lesson editing, coupons, emails to students and comments are not in it. Setup and FAQ: https://cotlet.dev/integrations/teachable-api-mcp-server
Build Discord communities with AI: roles, channels, modules, automations and reviewed announcements.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceControl your Discord server with AI. Lets you manage channels, roles, members, messages, and more through natural language.203 npmMIT
- FlicenseNot gradedqualityDmaintenanceThis server enables AI assistants to directly control the Unity Editor via MCP, supporting scene manipulation, script editing, level generation, monetization management, build pipelines, and more—all with zero external dependencies.-
- AlicenseBqualityDmaintenanceAn MCP server that enables AI agents to manage a Frappe LMS instance, including creating courses, chapters, lessons, quizzes, enrollments, batches, and certificates.39MIT
- AlicenseNot gradedqualityBmaintenanceEnables autonomous Discord server administration via natural language, allowing users to delegate tasks like channel/role creation, permission checks, and automations to an AI agent with safety gates and audit trails.MIT