Teachable MCP server for ChatGPT and Claude

Teachable connects to ChatGPT, Claude and other AI agents through Cotlet.dev's remote MCP server and your signed-in Cloud Browser. Your agent works on the courses, users, sales and reports screens your own login opens. The live integration page, checked 20 November 2026, describes Teachable's own experimental local MCP server for Claude and its API on Growth and higher plans.

What you can ask

Which students bought Photo Basics in the last 30 days and have not started it yet?

Send me last week's sales by course, with refunds.

Which lectures in Photo Basics do students complete least?

Draft an email to students who have not logged in for 30 days. Send nothing until I say so.

Export the student list of Portrait Lighting as a CSV.

Four students finished Photo Basics this week. Prepare their enrollment in Lightroom Essentials and show me first.

Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.

ChatGPT

Open Plugins > Add > Add custom MCP server. Name it Cotlet and use https://cotlet.dev/mcp/v1/connect with OAuth. Enable Developer mode in Settings > Security and login if the option is missing. Connect Cotlet, allow access, then select @Cotlet in a new chat.

Claude

Open Connectors > Add > Add custom connector. Name it Cotlet and use https://cotlet.dev/mcp/v1/connect. Allow access, then enable Cotlet under the plus button > Connectors in a chat.

Claude Code

claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"

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 Teachable 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.

Clone this repository and run python3 teachable_agent.py serve with COTLET_API_KEY set.

Or with Docker:

docker build -t teachable-mcp .
docker run -i --rm -e COTLET_API_KEY teachable-mcp

The local server exposes seven helpers for the hosted browser tools.

Local tools: teachable_guide, teachable_status, teachable_open, teachable_read, teachable_click, teachable_type, teachable_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. Run from this repo:

export COTLET_API_KEY="your-key"
python3 teachable_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 teachable_agent.py status    # is Teachable ready in your Cotlet.dev account
python3 teachable_agent.py guide     # Teachable screens and sign-in link
python3 teachable_agent.py read      # open Teachable, read the page, close the browser
python3 teachable_agent.py tools     # list Cotlet.dev tools
python3 teachable_agent.py serve     # start the stdio MCP server (same as no argument)

Questions from Teachable users

Is this an official Teachable integration?

No. Cotlet.dev is independent and not affiliated with Teachable.

Does Teachable offer its own MCP server?

The live page checked 20 November 2026 describes an experimental local MCP server for Claude on Growth and higher plans. Teachable also offers an API. Use the official integrations when they cover your task.

How do I sign in?

Open sso.teachable.com in your Cotlet Cloud Browser and sign in yourself. Enter any sign-in code there yourself.

When should the agent ask me?

Ask your agent to show proposed enrollments, course changes and student emails, and wait for your approval before applying them.

What access does the agent have?

The agent works on the screens your own Teachable login opens. Keep payouts, refunds and school payment settings in your own hands.

Live integration

Teachable tools and connection guide

More: https://cotlet.dev/integrations/teachable-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=teachable

Start free: https://cotlet.dev/signup?app=teachable&utm_source=github&utm_medium=readme&utm_campaign=teachable

MCP Server ยท Populars

MCP Server ยท New

    kitfunso

    Hippo

    One memory for every agent you'll ever use. Hippo writes what you teach a coding agent into a store in your repo, and your other agents read that same store.

    Community kitfunso
    Avazbek22

    DevProjex: MCP / GUI / CLI / TUI all in one

    Repomix alternative with up to 40% fewer tokens. Turn any codebase or Git repository into safe, token-efficient context for LLM and coding agents like Claude Code, Codex, and Cursor. GUI, TUI, CLI, and a read-only RAG MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, and code compression. Windows, macOS, Linux.

    Community Avazbek22
    membaseai

    Membase

    Memory layer for AI agents โ€” SDKs, CLI and MCP server for Membase

    Community membaseai
    dosco

    DeepORG โ€” One AI Agent for Your Whole Organization

    DeepORG (formerly GraphJin) โ€” one AI agent for your whole organization: databases, APIs, files, and code over MCP

    Community dosco
    scumble-app

    Scumble

    Free, open-source desktop editor for AI inpainting: select, prompt, get a colour-matched layer. FLUX 3 Image, FLUX.2, GPT Image, Nano Banana, Seedream and Qwen through your API key or your own ComfyUI. Layers, PSD export, MCP.

    Community scumble-app