Every page here is also plain Markdown, so a coding agent reads exactly what you read.
| What | Where |
|---|---|
| A map of every page | https://docs.fous.com/llms.txt |
| Every page in one file | https://docs.fous.com/llms-full.txt |
| One page as Markdown | Add .md to its URL, or send Accept: text/markdown. |
| The API contract | https://api.fous.com/openapi.json, OpenAPI 3.1 |
| An agent skill | https://fous.com/SKILL.md connects an agent with your API key. |
Copy page at the top of each page copies it as Markdown; the menu beside it opens the page in Claude or ChatGPT, copies a prompt for a coding agent, and links the .md file and llms.txt.
Prompt a coding agent
Paste this into Claude Code, Codex, Cursor or any agent that can read the web:
Fous docs for agents: https://docs.fous.com/llms.txt. Fetch it, then the .md pages your task needs; exact request and response shapes are in https://api.fous.com/openapi.json.
Fous docs index: https://docs.fous.com/llms.txt (append .md to any docs URL)
Fous API contract: https://api.fous.com/openapi.json
Key in FOUS_API_KEY; MCP: https://api.fous.com/mcp
With the MCP server connected, the agent can also search and run methods and manage workflows while it writes your code. A tool result's structuredContent is what the API returns, so code written against it works over the API. One difference: get_run answers a failed or canceled run with the run and its error, while GET /v1/runs/{id} answers with the error at its HTTP status.