Resources for your agent

Machine-readable versions of these docs: one-file docs, an installable agent skill, per-page Markdown, and an MCP server.

If you are integrating this API with a coding agent, hand it one of the machine-readable versions of these docs below rather than the rendered site.

Hand your agent one URL

Give it /llms-full.txt — every page of these docs concatenated into a single file, small enough to read in one fetch.

https://moonlakeai.mintlifysite.com/llms-full.txt

That is the fastest path and needs no setup.

Install the agent skill

/skill.md is a condensed guide written for agents: decision tables for when to quote versus generate and when to group assets under a project, a verification checklist, and the gotchas that trip up first integrations.

https://moonlakeai.mintlifysite.com/skill.md

If your tooling supports Agent Skills — Claude Code, Cursor, and others — save this into your skills directory so the guidance persists across sessions instead of being re-fetched each time. Agents can discover it themselves at /.well-known/agent-skills/index.json.

Everything available

Resource	Path	Use it for
All docs, one file	/llms-full.txt	The default. One fetch, whole corpus.
Agent skill	/skill.md	Persistent, condensed guidance with decision tables.
Page index	/llms.txt	Let an agent choose which pages to read.
Any page as Markdown	append .md to its URL	Reading one page without the site chrome.
OpenAPI spec	/openapi.json	Exact request and response schemas.
MCP server	/mcp	Search these docs as a tool, instead of fetching files.

Every page also answers with clean Markdown to a request sending Accept: text/markdown, and carries the API’s key rules at the top, so an agent that lands on any single page still gets them.

Two rules worth loading first

Both of these are the most common integration mistakes, and both are stated in every Markdown response:

1. POST /api/v1/assets returns a price quote and creates nothing. Resend the identical body with "mode": "generate" to actually run it.
2. Create a project with POST /api/v1/projects and pass its project_id on every related generation. Omit it and each request becomes its own single-asset project.

See Core concepts for the full vocabulary.