Prerender for AI agents
Prerender.io pre-renders JavaScript-heavy websites into static HTML so search engines can crawl and index them properly. SEO and engineering teams use it to improve how their site appears in search. 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 Prerender.
Recache a specific URL
Force a fresh prerender of a page after content changes so search engines see the update.
Check cache clear status read-only
Look up whether a requested cache clear has finished before verifying the fix.
Run an SEO audit report
Generate an SEO audit of prerendered pages to catch crawlability issues.
10 Prerender actions, graded by risk.
Every Prerender action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- prerender.list_v3List V3
- prerender.list_healthzList Healthz
- prerender.search_cached_urlsSearch Cached URLs
- prerender.get_prerendered_pageGet Prerendered Page
- prerender.check_healthCheck Health
write
3Create and change things. Allow, or ask the user first.
- prerender.create_seo_audit_reportCreate SEO Audit Report
- prerender.recache_urlRecache URL
- prerender.change_recache_speedChange Recache Speed
destructive
2Delete, cancel or archive. Ask first, or deny outright.
- prerender.clear_cacheClear Cache
- prerender.get_cache_clear_statusGet Cache Clear Status
Prerender in three steps.
- 01Your users connect PrerenderThey add their Prerender api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create SEO Audit Report” can wait for the user, and “clear Cache” can be denied outright.
- 03Any agent can actYour agent calls Prerender through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('prerender', { read: 'allow', write: 'ask', // create_seo_audit_report destructive: 'deny', // clear_cache }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Prerender connects.
Users add their Prerender 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 Prerender 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 Prerender from any agent.
Prerender and Arc0, answered.
Can I use Prerender with Claude, ChatGPT or Cursor?
Yes. Connect Prerender 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 Prerender actions you allow.
How do users connect Prerender?
Users add their Prerender 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 Prerender actions can my agent take?
10 in total: 5 read, 3 write and 2 destructive, such as “create SEO Audit Report”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Prerender?
Yes. Actions like “clear Cache” 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 Prerender too?
Yes. The same Prerender connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Prerender into your agent.
Your users connect Prerender once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan