Skip to main content
For agents: the full documentation index is at https://filecheck.io/docs/llms.txt. Fetch it to find any other page.
This page is written for AI agents. Give it to Claude Code, Codex, Cursor, VS Code or any agent that can run commands and edit its own settings, and it connects Filecheck for you. For ChatGPT and Claude, the agent tells you the two clicks to make yourself. Prefer to do it by hand? See MCP server.

Give your agent this prompt

Steps for the agent

  1. Get a secret key. Ask the user for a Filecheck secret key (sk_…). If they have none, they create one in the dashboard under Dev Hub → API keys, labelled for you. Never repeat the key back in chat. A publishable key (pk_…) does not work: it is for the storefront only.
  2. Add the server for the tool you run in, at user level, never in a project file that gets committed. Coding tools run the local server, which can read and save files on the user’s disk: The local server needs Node.js 18 or later (node --version).
  3. Load it. Reload or restart the MCP servers if your tool needs it (Claude Code: start a new session; Cursor: refresh in MCP settings; VS Code: MCP: List Servers, then start filecheck).
  4. Check it. Call list_catalog with type: "workflows" and show the user the workflows it returns.
  5. Report. Tell the user which file or setting you changed, and that revoking the key in the Dev Hub disconnects you.

Rules for the agent

  • Keep the key out of project files, scripts and commits. User-level settings or environment variables only.
  • A secret key can change anything in the account the API can. Use one key per agent.
  • Read both axes of every job: status says whether the check ran, outcome is the verdict. status: done with outcome: fail means the file is not print-ready.
  • If a tool returns pending: true, poll get_job with the job id. Never submit the same file again.
  • Download links expire after about an hour. Call get_job for fresh ones instead of storing them.
  • New workflows, rules and profiles stay drafts until published. Ask the user before you publish one, map a product, change storefront settings, or run test_destination (it writes a real file into the shop’s hotfolder).
  • Read a record’s schema with setup_reference before you create or patch it. Use dryRun: true when unsure. When the API refuses a record, the error names the field and lists every problem: fix them all, then retry.

What you can do next

  • Check a file for print: check_file with a preflight profile from list_catalog, then explain the verdict and each finding. Pass context (the ordered size, page count, bleed) when the user tells you what they ordered.
  • Fix what can be fixed with fix_file, then give the user the download link, or save it next to the original with save_artifact (local server).
  • Validate PDF/A or PDF/UA with validate_pdf; make a file smaller with optimize_file and settings from an optimize preset.
  • Explain why a past job failed: list_jobs, get_job, then get_report for the full report.
  • Set up a product, if the user asks: follow Set up products with AI. Build a draft profile, rule and workflow with manage_catalog, try it on a real file with check_file and its workflowId, then publish it and map_product (Shopify) when the user agrees.
  • Set up delivery: follow Set up delivery with AI. manage_destination, then test_destination once the user agrees, then add the destination to the workflow’s delivery.
  • Fix how the upload box appears on product pages with get_settings and update_settings.

Go deeper

MCP server

Connect by hand, client by client, and every tool.

Set up products with AI

Workflows, rules and profiles, as drafts first.

Verify jobs

The two-axis result model.

REST API

The same features for your own code.