Getting started
Quick start
Create an API key and make your first authenticated call in about two minutes.
1. Create an API key
- Sign in to CourseFoundry.
- Go to Settings → MCP API Keys.
- Click Create key, give it a name, and choose a scope - Read + Write or Read-only.
- Copy the key immediately. It starts with
cfry_and is shown only once.
Keep keys secret. They are tied to your account and are hashed (SHA-256) at rest - CourseFoundry cannot recover a lost key, so regenerate if you lose it.
2. Make your first call
List the tools the endpoint exposes. This confirms your key works:
bash
curl -X POST https://www.coursefoundry.com/api/mcp \
-H "Authorization: Bearer cfry_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'A successful response returns the list of 13 available tools. Now list your courses:
bash
curl -X POST https://www.coursefoundry.com/api/mcp \
-H "Authorization: Bearer cfry_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"method": "tools/call",
"params": { "name": "list_courses", "arguments": {} },
"id": 1
}'Always use
www.coursefoundry.com. The bare domain issues a 308 redirect that drops the request body in many clients (curl, Postman, GitHub Actions).
3. Connect Claude Code (optional)
If you use Claude Code, register CourseFoundry as an MCP server and skip the raw HTTP entirely:
bash
claude mcp add --transport http coursefoundry https://www.coursefoundry.com/api/mcp \
--header "Authorization: Bearer cfry_YOUR_KEY"Then just ask, in plain language:
- “List my CourseFoundry courses”
- “Create a new course called Intro to Python with 5 lessons”
- “Run the assessment workflow on lesson [id] in course [id]”
Next steps
- MCP server reference - full protocol, Claude Code, GitHub Actions, ChatGPT.
- API reference - every tool, resource, prompt, and AI workflow.
- AI-readable courses - expose your published courses to assistants.