Zyte Api for AI agents
Zyte API automates web data extraction, handling bans and dynamic content, used by data teams pulling structured data from websites at scale. 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 Zyte Api.
Extract data from a URL
Pull structured content from a page, handling anti-bot defenses automatically.
Check for active incidents
Look up whether the service is experiencing an outage before relying on it for a job.
Check scheduled maintenance
Read upcoming maintenance windows before scheduling a large extraction job.
7 Zyte Api actions, graded by risk.
Every Zyte Api 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.
- zyte_api.list_incidentsList Zyte API status incidents
- zyte_api.get_unresolved_incidentsZyte API: Get Unresolved Incidents
- zyte_api.get_scheduled_maintenancesGet scheduled maintenances
- zyte_api.extract_zyte_apiExtract Data from URL
write
3Create and change things. Allow, or ask the user first.
- zyte_api.statusGet Zyte API Status Rollup
- zyte_api.componentsZyte API Components
- zyte_api.active_scheduled_maintenancesFetch Active Scheduled Maintenances
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Zyte Api in three steps.
- 01Your users connect Zyte ApiThey add their Zyte Api api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “get Zyte API Status Rollup” can wait for the user to approve.
- 03Any agent can actYour agent calls Zyte Api through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('zyte_api', { read: 'allow', write: 'ask', // status destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Zyte Api connects.
Users add their Zyte Api 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 Zyte Api 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 Zyte Api from any agent.
More web data and scraping apps.
Zyte Api and Arc0, answered.
Can I use Zyte Api with Claude, ChatGPT or Cursor?
Yes. Connect Zyte Api 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 Zyte Api actions you allow.
How do users connect Zyte Api?
Users add their Zyte Api 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 Zyte Api actions can my agent take?
7 in total: 4 read, 3 write and 0 destructive, such as “get Zyte API Status Rollup”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Zyte Api?
Yes. Allow read actions and deny writes in the Zyte Api policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Zyte Api too?
Yes. The same Zyte Api connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Zyte Api into your agent.
Your users connect Zyte Api 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