Builder.io for AI agents
Builder.io is a visual platform for managing website content, models, and assets, letting marketing and product teams update pages without waiting on a developer. 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 Builder.io.
Create a content entry
Add a new content entry to a model, such as a landing page section or blog draft.
Check what's currently live
Fetch a content entry to see what's published before changing anything on top of it.
Confirm before deleting an entry
Confirm before deleting a content entry, since anything referencing it on a live page would break.
10 Builder.io actions, graded by risk.
Every Builder.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- builder_io.list_assetsList Assets
- builder_io.list_modelsList Models
- builder_io.list_space_usersList Space Users
- builder_io.get_content_entryGet Content Entry
- builder_io.get_space_detailsGet Space Details
- builder_io.list_content_entriesList Content Entries
- builder_io.list_content_foldersList Content Folders
write
2Create and change things. Allow, or ask the user first.
- builder_io.create_content_entryCreate Content Entry
- builder_io.update_content_entryUpdate Content Entry
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- builder_io.delete_content_entryDelete Content Entry
Builder.io in three steps.
- 01Your users connect Builder.ioThey add their Builder.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Content Entry” can wait for the user, and “delete Content Entry” can be denied outright.
- 03Any agent can actYour agent calls Builder.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('builder_io', { read: 'allow', write: 'ask', // create_content_entry destructive: 'deny', // delete_content_entry }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Builder.io connects.
Users add their Builder.io 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 Builder.io 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 Builder.io from any agent.
Builder.io and Arc0, answered.
Can I use Builder.io with Claude, ChatGPT or Cursor?
Yes. Connect Builder.io 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 Builder.io actions you allow.
How do users connect Builder.io?
Users add their Builder.io 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 Builder.io actions can my agent take?
10 in total: 7 read, 2 write and 1 destructive, such as “create Content Entry”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Builder.io?
Yes. Actions like “delete Content Entry” 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 Builder.io too?
Yes. The same Builder.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Builder.io into your agent.
Your users connect Builder.io 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