Renderform for AI agents
RenderForm automates image and PDF generation from templates, letting teams produce visuals with dynamic text, images, and QR codes. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Renderform.
Generate an image from a template
Fill a saved template with a customer's name and order details to produce a personalized graphic.
Capture a website screenshot
Take a screenshot of a landing page URL for use in a report or presentation.
Check results before cleanup
List existing rendered results, then delete an old one only after confirming it's no longer needed.
7 Renderform actions, graded by risk.
Every Renderform action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- renderform.get_resultGet Result
- renderform.list_fontsList Fonts
- renderform.list_results_v2List Results (v2)
- renderform.list_templates_v2List Templates V2
write
2Create and change things. Allow, or ask the user first.
- renderform.create_pdf_from_urlCreate PDF from URL
- renderform.take_screenshotTake Website Screenshot
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- renderform.delete_resultDelete Result
Renderform in three steps.
- 01Your users connect RenderformThey add their Renderform api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create PDF from URL” can wait for the user, and “delete Result” can be denied outright.
- 03Any agent can actYour agent calls Renderform through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('renderform', { read: 'allow', write: 'ask', // create_pdf_from_url destructive: 'deny', // delete_result }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Renderform connects.
Users add their Renderform api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Renderform connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Renderform from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Renderform and Arc0, answered.
Can I use Renderform with Claude, ChatGPT or Cursor?
Yes. Connect Renderform to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Renderform actions you allow.
How do users connect Renderform?
Users add their Renderform api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Renderform actions can my agent take?
7 in total: 4 read, 2 write and 1 destructive, such as “create PDF from URL”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Renderform?
Yes. Actions like “delete Result” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Renderform too?
Yes. The same Renderform connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Renderform into your agent.
Your users connect Renderform once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan