Hystruct for AI agents

Hystruct is an AI-driven web scraping tool that extracts structured data from websites using predefined schemas. Teams use it to pull this data on a schedule instead of copying it by hand. 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.

Web data and scrapingAPI keyMCP + RESThystruct.com
AUDIT LOG · HYSTRUCTPOLICY: acme-support
09:41:07 · claude · u_8f2read
hystruct.list_all_webhooks
List All Webhooks✓ allowed · 212ms
EVERY HYSTRUCT CALL, ON THE RECORD
01 · USE CASES

What agents do in Hystruct.

01

Check configured webhooks

List webhooks configured on the account to confirm extraction results are routed correctly.

02

Review extraction schema setup

Review a scraping schema's field mapping, read-only, before it is used on a new site.

03

Confirm webhook delivery target

Confirm the destination URL on a webhook before extracted data starts flowing to it.

02 · ACTIONS

1 Hystruct actions, graded by risk.

Every Hystruct action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

1

Look things up. Allowed by default.

  • hystruct.list_all_webhooks
    List All Webhooks

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Hystruct in three steps.

  1. 01Your users connect HystructThey add their Hystruct api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Hystruct through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('hystruct', {
  read: 'allow',
  write: 'ask',        
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Hystruct connects.

Users add their Hystruct 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 Hystruct 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
05 · WORKS WITH

Use Hystruct from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Hystruct and Arc0, answered.

Q01

Can I use Hystruct with Claude, ChatGPT or Cursor?

Yes. Connect Hystruct 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 Hystruct actions you allow.

Q02

How do users connect Hystruct?

Users add their Hystruct 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.

Q03

Which Hystruct actions can my agent take?

1 in total: 1 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Hystruct?

Yes. Allow read actions and deny writes in the Hystruct policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Hystruct too?

Yes. The same Hystruct connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Hystruct into your agent.

Your users connect Hystruct once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan