Byteforms for AI agents
Byteforms builds online forms and manages the responses they collect, keeping form data and integrations in one place for a small team. 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 Byteforms.
Create a new form
Create a new form for collecting sign-ups or feedback, ready to share with a link.
Pull in form responses
Pull the responses submitted to a form to review before importing them elsewhere.
Confirm before deleting a form
Confirm before deleting a form, since every response it collected is removed along with it.
5 Byteforms actions, graded by risk.
Every Byteforms action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- byteforms.get_all_forms2Get All Forms
- byteforms.get_form_by_idGet Form By ID
- byteforms.get_form_responsesGet Form Responses
write
1Create and change things. Allow, or ask the user first.
- byteforms.create_formCreate form
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- byteforms.delete_formDelete Form
Byteforms in three steps.
- 01Your users connect ByteformsThey add their Byteforms api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create form” can wait for the user, and “delete Form” can be denied outright.
- 03Any agent can actYour agent calls Byteforms through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('byteforms', { read: 'allow', write: 'ask', // create_form destructive: 'deny', // delete_form }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Byteforms connects.
Users add their Byteforms 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 Byteforms 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 Byteforms from any agent.
Byteforms and Arc0, answered.
Can I use Byteforms with Claude, ChatGPT or Cursor?
Yes. Connect Byteforms 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 Byteforms actions you allow.
How do users connect Byteforms?
Users add their Byteforms 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 Byteforms actions can my agent take?
5 in total: 3 read, 1 write and 1 destructive, such as “create form”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Byteforms?
Yes. Actions like “delete Form” 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 Byteforms too?
Yes. The same Byteforms connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Byteforms into your agent.
Your users connect Byteforms once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan