Teachable MCP Server
Course content, coupons, emails and comments on any plan.
Hosted MCP Server
npx add-mcp 'https://cotlet.dev/mcp/v1/teachable'Installs into Claude Code, Codex, Cursor and more
Documentation
Cotlet · Integrations · How it works · Security · For developers · For automation agencies · Blog · API docs · Help center · Changelog · Contact · Pricing · Sign up
Teachable API and MCP server
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.
Course content, coupons, emails and comments on any plan. Use it in ChatGPT, Claude or any AI agent over MCP, or in n8n, Make and scripts over REST.
Platform for creating and selling online courses, coaching and digital downloads from your own school.
What is the Teachable API?
Cotlet's Teachable API exposes 15 endpoints for your own Teachable account: list courses, get curriculum, get lesson, list students, list comments, list coupons, create lesson, update lesson, publish lesson, create coupon, archive coupon, enroll student, send email, reply to comment and moderate comment. The list_courses endpoint returns courses in your school with name, published state and URL. Each endpoint takes simple JSON inputs like course_id, lesson_id or body_markdown and works both as an operation of the teachable_read or teachable_write MCP tool for agents and as a REST call for scripts.
- Category: Courses & training
- Endpoints: 15 (6 read, 9 write)
- Updated: 2026-11-11
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). Cotlet is a hosted MCP server and REST API for Teachable with 15 endpoints (6 read, 9 write): you sign in once in your own cloud browser, your AI agent does the work.
Does Teachable have an official 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.
| Task | Teachable official | Cotlet |
|---|---|---|
| List courses and read lesson content | Partly: Growth plan and up, read only | Yes |
| List the students of a course | Partly: Growth plan and up | Yes |
| Enroll a student in a course | Partly: Growth plan and up; Zapier has an Enroll User in Course action | Yes |
| Create, edit and publish lessons | No: The API reads a lecture and marks it complete for a student | Yes |
| Create and archive coupons | No | Yes |
| Email the students of a course | No | Yes |
| Approve, deny and reply to comments | No: Zapier has a New Comment trigger only | Yes |
Sources: Teachable API quickstart (Growth plan or higher, API key), Teachable API reference index, Teachable MCP, experimental (help center), Teachable on Zapier: 20 triggers, 4 actions, 1 search, Teachable Help: Course Comments (moderation, Pending Approval), Teachable Help: Price your products (coupons)
Quick reference
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.
Cotlet provides a hosted MCP server and REST API for Teachable: 15 tools (6 read, 9 write).
Access Sign up at https://cotlet.dev/app/signup?app=teachable and request the app in the Cotlet console. ChatGPT and Claude connect with OAuth at https://cotlet.dev/mcp/v1/connect, no API key; code editors and scripts use an API key from the console.
MCP server https://cotlet.dev/mcp/v1
MCP tools teachable_read, teachable_write, reads and writes apart; call one with {"operation": "<operation>", "arguments": {...}}
REST base https://cotlet.dev/api/v1/teachable, each operation at its own route, e.g. POST /api/v1/teachable/coupons
Auth Authorization: Bearer <COTLET_API_KEY>. Listing endpoints and schemas needs no key; calling an endpoint needs one. Over MCP the input schemas come with sign-in.
Operations list_courses, get_curriculum, get_lesson, list_students, list_comments, list_coupons, create_lesson, update_lesson, publish_lesson, create_coupon, archive_coupon, enroll_student, send_email, reply_to_comment, moderate_comment
Confirm update_lesson, publish_lesson, create_coupon, archive_coupon, enroll_student, send_email, reply_to_comment, moderate_comment (by default the user approves each call; the user can switch this off per tool, e.g. for scheduled automations)
Markdown https://cotlet.dev/integrations/teachable-api-mcp-server.md
How access works:
1. The user signs up at https://cotlet.dev/app/signup?app=teachable and requests Teachable in the Cotlet console.
2. The user signs in to Teachable once in their Cotlet Cloud Browser (their own Chrome in the cloud, opened from the console) and enables Teachable for agents. An agent cannot do this step.
3. ChatGPT and Claude: the user adds https://cotlet.dev/mcp/v1/connect as a connector and signs in to Cotlet (OAuth). Code editors and scripts: an API key from the console goes into the MCP client or the REST call as a bearer token.
Fits: people who want a hosted Teachable server that someone else maintains, including non-developers. Developers who prefer to run and fix code on their own computer can use an open-source Teachable MCP server instead.
Policy: Cotlet never stores passwords and never bypasses MFA.
Company: legal details in the Terms of service at https://cotlet.dev/terms. Contact contact@cotlet.dev.
Sign-in: the user signs in to Teachable in their own Cloud Browser, a Chrome Cotlet runs for them in the EU; password saving is off, the profile is AES-256-GCM encrypted, and agents get Teachable only after the user enables it. Calls are requests from that browser's IP with its cookies, each listed in the user's Background activity. Disable for agents, signing out in the browser or Reset browser cuts access. Cotlet is run by Take Group sp. z o.o. (EU VAT PL6342984273).
API key: holds no Teachable login or cookies, only asks Cotlet to run a tool. Each key is scoped to chosen apps and tools, read only or read and write. Actions that reach other people wait for the user's approval by default, so a leaked key cannot post or message as the user. Every call is in the activity log; deleting the key ends access at once.
Terms: the user stays responsible for following Teachable's terms; Cotlet is not affiliated with Teachable.
What can an AI agent do in Teachable?
Cotlet is best for Teachable course creators who run their school without a developer and want their AI agent to edit lessons, create coupons, email students and answer comments without running or fixing a server.
- Create coupon codes for a sale: "Make a 30% coupon BLACKFRIDAY26 for all courses, 100 uses, ending 1 December. Check first that the code is free." →
list_coupons,create_coupon,archive_coupon - Email all students of a course: "Email everyone in the Python course that the live Q&A moved to Thursday." →
list_courses,send_email - Moderate and answer lesson comments (runs: daily): "Go through the Pending Approval comments in all my courses: approve real questions, deny spam, and draft an answer to each question from the lesson." →
list_comments,get_curriculum,get_lesson,moderate_comment,reply_to_comment - Update lessons from Markdown files: "Compare my Python course with the Markdown files in ./scripts, update the lessons that changed, and ask me before touching published ones." →
list_courses,get_curriculum,get_lesson,update_lesson,create_lesson,publish_lesson - Enroll students from a CSV: "Add the 12 new hires from team.csv to the Onboarding course." →
list_courses,enroll_student
Can Teachable automations run on a schedule in n8n, Make or Zapier?
Yes. Cotlet does not replace your automation platform: it gives it a Teachable connection it does not have, with the same API key as your agent. Write actions ask for your OK by default; switch that off in your dashboard for the tools you choose, for example to moderate and answer lesson comments, and the schedule runs on its own. Cotlet runs in the cloud, so it keeps going while your computer is off.
| Where | How to connect | How to schedule |
|---|---|---|
| Your AI agent | Add https://cotlet.dev/mcp/v1 with your API key. | A scheduled agent run, for example a Claude Code routine. |
| n8n | MCP Client node with https://cotlet.dev/mcp/v1, or an HTTP Request node with the endpoint's method and URL, such as GET https://cotlet.dev/api/v1/teachable/comments. | Schedule Trigger node. |
| Make | HTTP module: the endpoint's method and URL with an Authorization: Bearer header, and a JSON body for POST, PUT and PATCH. | Scenario schedule. |
| Zapier | Webhooks by Zapier, Custom Request: the same method, URL, header and body. | Schedule by Zapier trigger. |
| Your own script | GET https://cotlet.dev/api/v1/teachable/comments with your API key. | cron or GitHub Actions. |
Tools
For AI agents: Every endpoint and its schema is public. The 15 endpoints on this page, with parameters and example responses, can be listed without an account. Calling one returns 401 without an API key and 403 while the key has no access to Teachable.
list_courses
Courses in your school with name, published state and URL. Access: read. REST: GET /api/v1/teachable/courses. MCP: teachable_read → list_courses.
| Parameter | Type | Required | Description |
|---|---|---|---|
published | boolean | no | Only published courses. Default: all. |
Returns every course in your school, in the order the Courses page shows them. Use course_id from each item in the other tools. Set published to see only the courses students can enroll in.
Example response:
{
"courses": [
{
"course_id": "1204512",
"name": "Python for Beginners",
"published": true,
"url": "https://yourschool.teachable.com/p/python-for-beginners"
},
{
"course_id": "1260077",
"name": "Team Onboarding",
"published": false,
"url": "https://yourschool.teachable.com/p/team-onboarding"
}
]
}
get_curriculum
Sections and lessons of a course, in order, with published and public preview flags. Access: read. REST: GET /api/v1/teachable/courses/{course_id}/curriculum. MCP: teachable_read → get_curriculum.
| Parameter | Type | Required | Description |
|---|---|---|---|
course_id | string | yes | Course ID from list_courses. |
Returns the Curriculum tab of one course: sections in order, and the lessons inside each section in order. Each lesson has a published flag and a public preview flag. Use lesson_id with get_lesson, update_lesson and publish_lesson.
Example response:
{
"course_id": "1204512",
"sections": [
{
"section_id": "9120331",
"name": "Basics",
"lessons": [
{
"lesson_id": "35120871",
"name": "Lesson 1: Welcome",
"published": true,
"public_preview": true
},
{
"lesson_id": "35120874",
"name": "Lesson 3: Functions",
"published": true,
"public_preview": false
}
]
}
]
}
get_lesson
Lesson content as blocks: text as Markdown, plus the type of each video, PDF, audio, quiz and other block. Access: read. REST: GET /api/v1/teachable/courses/{course_id}/lessons/{lesson_id}. MCP: teachable_read → get_lesson.
| Parameter | Type | Required | Description |
|---|---|---|---|
course_id | string | yes | Course ID from list_courses. |
lesson_id | string | yes | Lesson ID from get_curriculum. |
Returns the blocks of one lesson in the order the lesson editor shows them. Text & Image blocks come back as Markdown with a block_id. Other blocks (video, PDF viewer, audio, resource, quiz and so on) come back with their type and title only.
Example response:
{
"lesson_id": "35120874",
"name": "Lesson 3: Functions",
"published": true,
"blocks": [
{
"block_id": "b_5521",
"type": "text_and_image",
"body_markdown": "# Functions\n\nA function groups steps you want to reuse."
},
{
"block_id": "b_5522",
"type": "video",
"title": "Functions in 6 minutes"
}
]
}
list_students
Students with name, email and join date, or the students of one course. Access: read. REST: GET /api/v1/teachable/students. MCP: teachable_read → list_students.
| Parameter | Type | Required | Description |
|---|---|---|---|
course_id | string | no | Only students enrolled in this course. |
limit | integer | no | 1 to 100. Default: 50. |
cursor | string | no | Next page cursor from the previous call. |
Lists students of your school, newest first. Pass course_id to list only the students enrolled in one course. Pages hold up to 100 students; pass next_cursor back as cursor for the next page. Use the emails with send_email when you need part of a course.
Example response:
{
"students": [
{
"user_id": "70418822",
"name": "Maria Kowal",
"email": "maria.kowal@example.com",
"joined_at": "2026-09-28T10:14:00Z"
}
],
"next_cursor": null
}
list_comments
Lesson comments across your school or one course, with author, lesson, status and unread flag. Access: read. REST: GET /api/v1/teachable/comments. MCP: teachable_read → list_comments.
| Parameter | Type | Required | Description |
|---|---|---|---|
course_id | string | no | Only comments in this course. Default: all courses. |
status | enum | no | all, pending or denied. Default: all. |
unread_only | boolean | no | Only comments you have not marked as read. |
limit | integer | no | 1 to 100. Default: 50. |
cursor | string | no | Next page cursor from the previous call. |
Lists comments the way Site, Comments does, newest first. Status pending returns the Pending Approval queue, which exists only when Comment moderation is on; denied returns comments you denied, which stay in your admin. Use comment_id with moderate_comment and reply_to_comment.
Example response:
{
"comments": [
{
"comment_id": "88120431",
"course_id": "1204512",
"lesson": "Lesson 3: Functions",
"author": "Maria Kowal",
"body": "Can a function return two values?",
"status": "pending",
"unread": true,
"created_at": "2026-10-09T14:32:00Z"
}
],
"next_cursor": null
}
list_coupons
School and product coupons with code, discount, uses, expiry and status. Access: read. REST: GET /api/v1/teachable/coupons. MCP: teachable_read → list_coupons.
| Parameter | Type | Required | Description |
|---|---|---|---|
include_archived | boolean | no | Also list archived coupons. Default: false. |
Returns the coupons from the Coupons page: school coupons (all products or one product type) and product coupons (one pricing plan). Archived coupons are left out unless you ask for them. Check the list before create_coupon so a code is not used twice.
Example response:
{
"coupons": [
{
"coupon_id": "3917702",
"name": "Summer sale",
"code": "SUMMER20",
"discount": "20%",
"applies_to": "all_products",
"expires_at": "2026-09-01",
"quantity": 500,
"used": 212,
"status": "archived"
}
]
}
create_lesson
New unpublished lesson at the end of a section, with text from Markdown. Access: write. REST: POST /api/v1/teachable/courses/{course_id}/lessons. MCP: teachable_write → create_lesson.
| Parameter | Type | Required | Description |
|---|---|---|---|
course_id | string | yes | Course ID from list_courses. |
section_id | string | yes | Section ID from get_curriculum. |
title | string | yes | Lesson name. |
body_markdown | string | no | Text for a Text & Image block. Images by URL. |
Adds a lesson to a section, like New lesson in the Curriculum tab. New lessons start unpublished, so no student sees it until publish_lesson runs. That is why create_lesson runs without asking first.
Example response:
{
"lesson_id": "35120990",
"name": "Lesson 4: Loops",
"section_id": "9120331",
"published": false
}
update_lesson
Rename a lesson or replace the text of its Text & Image block. Other blocks stay as they are. Access: write, asks the user first. REST: PATCH /api/v1/teachable/courses/{course_id}/lessons/{lesson_id}. MCP: teachable_write → update_lesson.
| Parameter | Type | Required | Description |
|---|---|---|---|
course_id | string | yes | Course ID from list_courses. |
lesson_id | string | yes | Lesson ID from get_curriculum. |
title | string | no | New lesson name. |
body_markdown | string | no | New text for the Text & Image block. |
block_id | string | no | Text & Image block ID from get_lesson. Default: the first one. |
Renames a lesson and replaces the text of one Text & Image block; video, PDF, audio and quiz blocks are not touched. Teachable saves edits to a published lesson live at once, so students see the change right away. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"lesson_id": "35120874",
"name": "Lesson 3: Functions",
"updated_block_id": "b_5521",
"published": true,
"updated_at": "2026-10-11T09:20:00+02:00"
}
publish_lesson
Publish a lesson so enrolled students see it, or unpublish it. Access: write, asks the user first. REST: POST /api/v1/teachable/courses/{course_id}/lessons/{lesson_id}/publish. MCP: teachable_write → publish_lesson.
| Parameter | Type | Required | Description |
|---|---|---|---|
course_id | string | yes | Course ID from list_courses. |
lesson_id | string | yes | Lesson ID from get_curriculum. |
published | boolean | no | false unpublishes. Default: true. |
Does what Publish and Unpublish do in the lesson editor. Unpublished lessons are hidden from students, and a section whose lessons are all unpublished is hidden too. The course itself must be published and enrollable on its Information tab. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"lesson_id": "35120874",
"published": true
}
create_coupon
Coupon code for all products, one product type or one pricing plan. Access: write, asks the user first. REST: POST /api/v1/teachable/coupons. MCP: teachable_write → create_coupon.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | yes | Internal name, for your own list. |
code | string | yes | Letters and numbers only. |
discount_type | enum | yes | percent or amount. |
discount | integer | yes | Percent off, or the fixed amount off. |
applies_to | enum | no | all_products, courses, coaching, digital_downloads, memberships, bundles or pricing_plan. Default: all_products. |
pricing_plan_id | string | no | Required when applies_to is pricing_plan. |
expires_at | date | no | Last day the code works. |
quantity | integer | no | Number available, 1 to 10000. |
Creates a coupon on the Coupons page. The code holds letters and numbers only. Quantity is the number available, up to 10,000. Teachable does not sell a paid product below $1.00 USD. The code takes money off your sales. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"coupon_id": "3918274",
"name": "Black Friday 2026",
"code": "BLACKFRIDAY",
"discount": "30%",
"applies_to": "courses",
"expires_at": "2026-12-01",
"quantity": 100,
"used": 0,
"status": "active"
}
archive_coupon
Unpublish a coupon so the code stops working. Archived codes can be used again. Access: write, asks the user first. REST: POST /api/v1/teachable/coupons/{coupon_id}/archive. MCP: teachable_write → archive_coupon.
| Parameter | Type | Required | Description |
|---|---|---|---|
coupon_id | string | yes | Coupon ID from list_coupons. |
Archives a coupon, which is how Teachable unpublishes one. Buyers who have the code can no longer use it. An archived code can be used for a new coupon later. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"coupon_id": "3917702",
"code": "SUMMER20",
"status": "archived"
}
enroll_student
Enroll a student in a course for free, adding them to your school first if the email is new. Access: write, asks the user first. REST: POST /api/v1/teachable/courses/{course_id}/student/enroll. MCP: teachable_write → enroll_student.
| Parameter | Type | Required | Description |
|---|---|---|---|
email | string | yes | Student email. |
course_id | string | yes | Course ID from list_courses. |
name | string | no | Full name, used when the student is new. |
Does what manual enrollment does in the Users menu: the student gets access to the course with no payment. A new email is added to your school first, because adding a student does not enroll them. Teachable sends no confirmation email for manual enrollments, and plan limits such as access duration or enrollment caps do not apply. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"user_id": "70418901",
"email": "maria.kowal@example.com",
"course_id": "1204512",
"status": "enrolled",
"user_created": true,
"confirmation_email_sent": false
}
send_email
Send an email from your school to chosen users, the students of a course or all users, as on the Emails, Compose page. Access: write, asks the user first. REST: POST /api/v1/teachable/emails. MCP: teachable_write → send_email.
| Parameter | Type | Required | Description |
|---|---|---|---|
to | enum | yes | users, course or all_users. |
user_emails | string[] | no | Recipients when to is users. |
course_id | string | no | Recipients when to is course. |
subject | string | yes | Email subject. |
body_markdown | string | yes | Email body. |
Sends a custom email from your school. Students who opted out of instructional and promotional emails in their profile do not receive it. To reach part of a course, take the emails from list_students and pass them in user_emails. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"email_id": "em_4471",
"to": "course",
"course_id": "1204512",
"subject": "Live Q&A moved to Thursday",
"status": "sent",
"sent_at": "2026-10-11T09:30:00+02:00"
}
reply_to_comment
Reply to a lesson comment as the school owner. The reply is public to the course. Access: write, asks the user first. REST: POST /api/v1/teachable/comments/{comment_id}/replies. MCP: teachable_write → reply_to_comment.
| Parameter | Type | Required | Description |
|---|---|---|---|
comment_id | string | yes | Comment ID from list_comments. |
body | string | yes | Reply text. |
Posts a reply under one comment, as the Reply button does in your comment admin. Comments are public and cannot be made private, so the whole course sees the reply. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"reply_id": "88120502",
"comment_id": "88120431",
"status": "published"
}
moderate_comment
Approve or deny a comment held in Pending Approval. Access: write, asks the user first. REST: POST /api/v1/teachable/comments/{comment_id}/moderate. MCP: teachable_write → moderate_comment.
| Parameter | Type | Required | Description |
|---|---|---|---|
comment_id | string | yes | Comment ID from list_comments. |
decision | enum | yes | approve or deny. |
Does what Approve and Deny do on a pending comment. An approved comment appears on the lesson. A denied comment stays in your comment admin with a Denied tag and is hidden from students. Pending Approval exists only when Comment moderation is on. By default you confirm each call; you can switch that off for this tool.
Example response:
{
"comment_id": "88120431",
"status": "approved"
}
How do I connect Teachable to ChatGPT, Claude, Cursor or Codex?
Connecting Teachable takes three steps: sign up, sign in to Teachable once in your Cloud Browser and enable it for agents, then add Cotlet to ChatGPT or Claude as a connector, with no API key, or add one MCP server or call the REST API with an API key.
Connect Teachable to your agent.
-
Create an account Sign up and add Teachable in the console. ChatGPT and Claude need no API key: you sign in to Cotlet when you add the connector. Code editors and scripts take an API key from the console.
-
Sign in to Teachable in your Cloud Browser Open your Cloud Browser in the console: your own Chrome in the cloud. Sign in to Teachable there yourself, the way you always do, then press Enable for agents, read only or read and write. We never save your password, and your agent keeps working even when your computer is off.
-
Add Cotlet to ChatGPT, Claude or your agent Paste the snippet for your client. The same server and key serve every app you connect, so you do this once.
ChatGPT:
Settings > Apps & Connectors > Create
MCP server URL: https://cotlet.dev/mcp/v1/connect
Authentication: OAuth
Claude:
Settings > Connectors > Add custom connector
URL: https://cotlet.dev/mcp/v1/connect
Claude Code:
claude mcp add --transport http cotlet \
https://cotlet.dev/mcp/v1 \
--header "Authorization: Bearer $COTLET_API_KEY"
Cursor:
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}
Codex:
# ~/.codex/config.toml
[mcp_servers.cotlet]
url = "https://cotlet.dev/mcp/v1"
bearer_token_env_var = "COTLET_API_KEY"
- Ask your agent Ask in plain words. Your agent finds the Teachable tools on the server and calls them for you; anything that reaches other people waits for your OK unless you switch that off for a tool.
Make a 30% coupon BLACKFRIDAY26 for all courses, 100 uses, ending 1 December. Check first that the code is free.
Call Teachable from your scripts.
- Export your API key Your scripts use the same API key as your agent. Keep it in an environment variable, never in your code.
export COTLET_API_KEY="cotlet_..."
- Call a tool Every tool is an endpoint under /api/v1/teachable with its own method and path, listed with the endpoints above. Path parameters go in the URL; the other parameters go in the query for GET and DELETE and in a JSON body otherwise.
curl -X POST https://cotlet.dev/api/v1/teachable/coupons \
-H "Authorization: Bearer $COTLET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"name":"Black Friday 2026","code":"BLACKFRIDAY","discount_type":"percent","discount":30,"applies_to":"courses","expires_at":"2026-12-01","quantity":100}'
- Read the result You get plain JSON back, ready for your script. A failed call costs nothing.
{
"coupon_id": "3918274",
"name": "Black Friday 2026",
"code": "BLACKFRIDAY",
"discount": "30%",
"applies_to": "courses",
"expires_at": "2026-12-01",
"quantity": 100,
"used": 0,
"status": "active"
}
How to use the Teachable REST API
Create your Cotlet API key
Create a Cotlet API key with access to Teachable and its read operations. Store it as COTLET_API_KEY in your environment or automation platform's credential store.
Connect Teachable in Cotlet and enable it for agents. Account access: Your own Teachable school owner account.
Make your first Teachable API request
REST:
curl https://cotlet.dev/api/v1/teachable/courses \
-H "Authorization: Bearer $COTLET_API_KEY"
Read courses and apply the operation limits
A successful REST call puts the tool output in result. This illustrative response excerpt omits call IDs, messages and credit details.
Illustrative response excerpt:
{
"status": "success",
"app": "teachable",
"tool": "list_courses",
"result": {
"courses": [
{
"course_id": "1204512",
"name": "Python for Beginners",
"published": true,
"url": "https://yourschool.teachable.com/p/python-for-beginners"
},
{
"course_id": "1260077",
"name": "Team Onboarding",
"published": false,
"url": "https://yourschool.teachable.com/p/team-onboarding"
}
]
}
}
Returns every course in your school, in the order the Courses page shows them. Use course_id from each item in the other tools.
Set published to see only the courses students can enroll in.
Keep the same selection when continuing a list. Compare changed record values as well as identifiers when refreshing your destination.
Teachable workflows for agents and automations
| Tool | Connect through | Example workflow |
|---|---|---|
| n8n | HTTP Request | Sections and lessons of a course, in order, with published and public preview flags. Use get_curriculum in your configured learning report. |
| Make | HTTP > Make a request | Lesson content as blocks: text as Markdown, plus the type of each video, PDF, audio, quiz and other block. Use get_lesson in your configured learning report. |
| Python or Node.js | REST API | Students with name, email and join date, or the students of one course. Use list_students in your configured learning report. |
Send Authorization: Bearer <your Cotlet API key> in request headers. You configure the schedule, destination and record comparisons.
Cotlet reads Teachable; your workflow steps write to your chosen destination. These HTTP workflows do not require a native Cotlet connector or a prebuilt template.
Python and Node.js can use the same HTTP requests without an AI agent. Keep access keys in credentials, outside shared workflow exports.
The API and MCP reference lists operations and inputs. The REST API guide explains authentication, errors and approvals.
Why use Cotlet for Teachable?
Built for agents
- One MCP server for every app you connect.
- The same tools as a REST API for scripts and cron jobs.
- Works with ChatGPT, Claude, Claude Code, Codex and Cursor.
Your login stays yours
- You sign in to Teachable yourself, in your own Cloud Browser. We never save your password; the profile is encrypted with AES-256-GCM, the cipher 1Password uses.
- A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory.
- The model never sees a login.
- No stored passwords, no MFA bypass.
You stay in control
- Scope each API key: its apps, its tools, read only or read and write.
- Anything that reaches other people waits for your OK, so a leaked key cannot post or message as you.
- Every background request listed in your Background activity. Disable for agents in one click.
Kept working for you
- We test every integration every 6 hours.
- When Teachable changes, the tool pauses until we fix it.
- Failed calls cost nothing.
Is it safe to connect Teachable to Cotlet?
Yes. You sign in to Teachable yourself, in your own Cloud Browser, and we never save your password. Your agents only get Teachable once you enable it, and every background request is listed. The browser profile is stored encrypted with AES-256-GCM, the same cipher 1Password uses for its vaults and Apple for iCloud Keychain. Independent public scanners grade cotlet.dev A+ and find it clean; click a result to rerun it yourself.
- A+ on Qualys SSL Labs: Encryption in transit: TLS setup and certificates, on all four server addresses. Live result
- A+ on securityheaders.com: Browser protections sent with every page, all six headers present. Live result
- A+ on Mozilla Observatory: Mozilla's web security baseline: score 120 of 100, 12 of 12 tests passed. Live result
- Clean on Sucuri SiteCheck: No malware, spam or defacement, and not on any of 9 blocklists, Google Safe Browsing included. Live result
How Cotlet protects your access
Common concerns
Who runs Cotlet?
Cotlet is run by Take Group, a Polish software company working since 2019. Take Group runs about 3,200 websites on its own systems and has its own DevOps team for infrastructure security. We built and used integrations like this inside the company for years before opening them as Cotlet.
Is this an official Teachable integration?
No, Cotlet is independent of Teachable. Teachable's own API is too limited for this work. Cotlet works through your own Teachable account, the way you use Teachable in the browser, so you need no partner approval and no developer setup.
What about client data and GDPR?
Cotlet is run from the EU and follows the GDPR. Cloud Browsers run in Finland, a Tier 1 country in the ITU Global Cybersecurity Index 2024. Data passes through a call and is not kept after it.
Can I start with read only?
Yes. Enable the app for agents as read only, or make the API key read only, and anything that reaches other people waits for your OK unless you switch that off per tool.
Is it reliable?
Every Cotlet service is checked every 3 minutes from Europe, North America, Asia and Australia. The live results and any outage are public at status.cotlet.dev.
How do I stop?
Press Disable for agents next to Teachable in your console: your agents lose access at once and you stay signed in. Signing out of Teachable in the browser works too, and Reset browser deletes the whole profile.
Is there a Teachable MCP server on GitHub?
Yes. Open-source Teachable MCP servers exist on GitHub, usually maintained by one person, and most of them wrap the public API, so they need a Growth plan and cannot edit lessons, create coupons or send emails. You install one on your own computer and keep it running yourself; when something changes, you or the maintainer fix it. Teachable also has an experimental MCP of its own, which runs locally and works with Claude Desktop only. Cotlet hosts a server that works in your school as you, and our team keeps it working.
| GitHub MCP server | Cotlet | |
|---|---|---|
| Setup | Clone or install the package, add your API key to each MCP client | Sign up, sign in to Teachable once, add one MCP server or API key |
| Plan needed | Growth plan or higher, for the API key | No API key: Cotlet signs in to your school like you do |
| What it can do | What the public API has: courses, lecture reads, users, enrollments, pricing plans, transactions | Lessons, coupons, emails to students and comments, plus courses and enrollments |
| When Teachable changes | It breaks until you or the maintainer fix it | Our team tests it daily and fixes it for you; failed calls are free |
| Your login | API key in a config file on your computer, valid until you revoke it | Signed in inside your own Cloud Browser in the EU, profile encrypted, disabled for agents in one click; if Teachable logs you out, your agent gets a link to sign in again |
| Where it runs | Your computer, while it is on | Hosted: Claude Code, Codex, Cursor, n8n and scripts, also on a schedule |
| Price | Free, paid for with your time | Free 7-day trial, then pay-as-you-go credit packs, no subscription |
Which one fits you
Pick Cotlet if
- you are not a developer, or you do not want to maintain a server
- you need it to keep working when Teachable changes, without checking it yourself
- your agent or a script should run it on a schedule, also while your computer is off
Pick an open-source server if
- you are comfortable installing, updating and fixing it yourself
- you want your sign-in to stay on your own computer
- you only need it now and then, from one MCP client
How much does the Teachable API cost?
Free 7-day trial with 2,000 credits, no card needed. After that, the Teachable API is pay as you go with no limit on apps: Credit packs from $29 for 5,000 credits, one-time, no subscription. A successful call uses 10 to 100 credits (10 for most tools, about $0.04 to $0.06), your Cloud Browser uses 50 credits a day while it has an app enabled for agents, however many apps that is, and an agent driving the browser itself uses 5 credits a minute. Credit packs stay valid for 12 months and stack, so unused credits carry over.
| Credits | Price, one time | Calls at 10 credits | Per 1,000 credits |
|---|---|---|---|
| 5,000 | $29 | 500 | $5.80 |
| 15,000 | $79 | 1,500 | $5.27 |
| 32,000 | $149 | 3,200 | $4.66 |
| 60,000 | $249 | 6,000 | $4.15 |
Only successful calls use credits; failed calls and timeouts cost nothing. At a balance of 0 calls pause, never a surprise charge. Authenticate with the Authorization: Bearer header. See full pricing
How Cotlet holds your access
Cotlet hosts MCP servers and REST APIs for apps with no usable API. Your agent works in your own Teachable account.
- Company details: Cotlet is run by Take Group sp. z o.o., a company registered in Poland. Its full address and registration numbers are in the Terms of service. Terms of service
- Your sign-in: You sign in to Teachable yourself, in your own Cloud Browser: a Chrome we run for you in the EU, one per app. We never save your password (password saving is off), the profile is stored encrypted with AES-256-GCM, and your agents get Teachable only after you enable it. When Teachable signs you out, your agent gives you a link to sign in again. Security
- Revoking access: Press Disable for agents next to Teachable, sign out of Teachable in your Cloud Browser, or reset the browser. Every background request is listed in your Background activity. Actions that reach other people wait for your OK unless you switch that off per tool.
- What we never do: Store passwords or bypass MFA.
- Teachable's terms: You use your own Teachable account and stay responsible for following Teachable's terms. Cotlet is independent and not affiliated with Teachable. Terms
- Contact: Questions about the company, security or an app: contact@cotlet.dev
Teachable API and MCP: questions
How do I get access?
Sign up free, open Teachable in the console and press Activate. Then you create your API key and connect Teachable there.
Do I need to be technical?
No. You sign in to Teachable once in your Cloud Browser, a normal Chrome you open from the console, and paste one command into your agent, or one URL into n8n. Your agent can walk you through it. There is no server to install, update or fix.
Is it safe to connect Teachable to Cotlet?
Yes. You sign in to Teachable yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Teachable once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.
Is a hosted server safer than a local one? My Teachable sign-in would leave my computer.
On Cotlet you sign in inside your own Cloud Browser, which only you open, and its profile is stored encrypted with AES-256-GCM in the EU. Agents get only the apps you enable, and every background request is listed. A local server keeps your Teachable cookie in a plain file on your computer, readable by any program you run, and stops when your computer is off.
Why does Cotlet send requests instead of clicking in my browser?
To be fast, Cotlet doesn't click through Teachable's pages. It sends the same requests your browser would, from your browser's IP with its cookies, without opening a window. Teachable sees the same browser and IP you signed in with, and every request is listed in your Background activity.
What if someone gets my Cotlet API key?
The key holds no Teachable login or cookies, it only asks Cotlet to run a tool. It can call only the apps and tools you gave it, and a read-only key changes nothing. Anything that reaches other people, like posts, comments or messages, waits for your OK in the dashboard by default, so a leaked key cannot post or message as you. When you switch approval off for a scheduled job, give that job its own key limited to that one tool. Every call is in your activity log, and deleting the key ends access at once.
Why a signed-in browser and not OAuth, like other integration platforms?
Teachable offers no OAuth token you can simply grant for these tools: its official API leaves them out or needs a developer app, a plan or an approval first (see the official API section above). That is why Cotlet sets the limits itself: per key, per tool, with your approval before anything reaches other people. Cotlet is run by Take Group sp. z o.o., an EU company (VAT PL6342984273).
How do I connect Teachable to ChatGPT or Claude?
Sign up at cotlet.dev, log in to Teachable once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Teachable account through Cotlet, in their phone apps too.
What can ChatGPT do in Teachable?
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Teachable: create coupon codes for a sale; email all students of a course; moderate and answer lesson comments. You ask in plain words, and anything that reaches other people waits for your OK first.
Do I need the Growth plan or an API key?
No. Cotlet signs in to your own school like you do, so it does not use the API key that Teachable's public API and its experimental MCP need on the Growth plan or higher. What you can change still follows what your account can do in the Teachable admin.
Will students get an email when my agent enrolls them?
No. Teachable sends no confirmation email for manual enrollments. If you want them to hear about it, send_email can write to them, and students who opted out of instructional and promotional emails do not receive it.
Can my agent post or send messages in Teachable without asking me?
No. Every call to update_lesson, publish_lesson, create_coupon, archive_coupon, enroll_student, send_email, reply_to_comment or moderate_comment waits for your OK by default. For scheduled automations you can switch confirmation off per tool in your dashboard, for example only for approvals. create_lesson runs without asking, because it sends nothing to anyone and one call undoes it.
Can I use the Teachable API in n8n?
Yes. Add https://cotlet.dev/mcp/v1 with your API key in n8n's MCP Client node, or call its endpoints under https://cotlet.dev/api/v1/teachable from the HTTP Request node.
Can I use the Teachable API without an AI agent?
Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.
Give your AI agents your signed-in browser.
Product: Integrations · How it works · Pricing · Security
Resources: Blog · API docs · Help center · Changelog · GitHub
Solutions: For developers · For automation agencies
Company: About · AI info: company facts · Contact
Legal: Terms of service · Privacy policy · Refund policy · Acceptable use · Cookie policy · DPA · Subprocessors
Elsewhere: Status page · Cotlet on GitHub · Cotlet on X · Cotlet on LinkedIn · Cotlet on Product Hunt · Cotlet on Crunchbase · Cotlet on SaaSHub
Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. About us
Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.