Agentql for AI agents
AgentQL connects AI agents to the web with a structured query language for extracting data and interacting with pages. Developers use it to automate browsing and data collection. 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 Agentql.
Query structured data from a page
Extract specific fields, like prices or listings, from a live web page using a structured query.
Check usage statistics
Review how many queries or browser sessions have been used this period before starting a new scrape.
Start a remote browser session
Open a new browser session to navigate a site before extracting data from it.
3 Agentql actions, graded by risk.
Every Agentql action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- agentql.get_usageGet AgentQL Usage Statistics
- agentql.query_dataQuery Data
write
1Create and change things. Allow, or ask the user first.
- agentql.create_remote_browser_sessionCreate Remote Browser Session
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Agentql in three steps.
- 01Your users connect AgentqlThey add their Agentql api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Remote Browser Session” can wait for the user to approve.
- 03Any agent can actYour agent calls Agentql through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('agentql', { read: 'allow', write: 'ask', // create_remote_browser_session destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Agentql connects.
Users add their Agentql 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 Agentql 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 Agentql from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore web data and scraping apps.
Agentql and Arc0, answered.
Can I use Agentql with Claude, ChatGPT or Cursor?
Yes. Connect Agentql 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 Agentql actions you allow.
How do users connect Agentql?
Users add their Agentql 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 Agentql actions can my agent take?
3 in total: 2 read, 1 write and 0 destructive, such as “create Remote Browser Session”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Agentql?
Yes. Allow read actions and deny writes in the Agentql policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Agentql too?
Yes. The same Agentql connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Agentql into your agent.
Your users connect Agentql once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan