
AgentQL MCP integration
Extract structured data from web pages and documents and create remote browser sessions.
Sign in, add AgentQL in Apps, then choose the account your AI can use.
Get started with AgentQL
- Add AgentQL to your Weavz workspace and connect the account you want to use.
- Review the available tools below and enable the actions your task needs. Check the account permissions before allowing changes.
- Connect a compatible AI client to your workspace, or use the actions API from your application.
Tools
| Name | Description |
|---|---|
Query Web Page or HTML query_dataExtract structured data from a public page URL or supplied HTML using a query or prompt. | Extract structured data from a public page URL or supplied HTML using a query or prompt. |
Query Document query_documentExtract structured data from an uploaded PDF or image. Each PDF page consumes an API call. | Extract structured data from an uploaded PDF or image. Each PDF page consumes an API call. |
Create Browser Session create_browser_sessionCreate a remote browser session and receive its CDP connection URL. Sessions consume provider resources. | Create a remote browser session and receive its CDP connection URL. Sessions consume provider resources. |
Quick Start
import { WeavzClient } from '@weavz-io/sdk'
const weavz = new WeavzClient({ apiKey: 'wvz_...' })
const result = await weavz.actions.execute('agentql', 'query_data', {
workspaceId: '550e8400-e29b-41d4-a716-446655440000',
integrationAlias: 'agentql',
input: { /* ... */ },
})Related Integrations
Explore integrations in other categories
Frequently Asked Questions
Is there a AgentQL MCP server through Weavz?
Yes. Add the AgentQL integration to a Weavz workspace, enable the actions you need and connect any required account. Weavz provides the workspace MCP endpoint in Tool Mode or Code Mode. The catalog currently lists 3 AgentQL actions.
What can an AI agent do with AgentQL?
Available actions include Query Web Page or HTML, Query Document, Create Browser Session. Your workspace exposes only the actions you enable. The agent also needs the intended account access and any required input values.
How do I connect AgentQL to Claude or ChatGPT?
Use a compatible remote MCP client, add the Weavz connector and choose a workspace. Add AgentQL, connect the required account and review the enabled actions. Client availability and account requirements vary; adding the connector does not authorize every app automatically.
Can I use AgentQL through an API or SDK?
Yes, supported actions can run through the Weavz REST API, TypeScript SDK or Python SDK. Configure a workspace and the required connections, use scoped access, and pass the intended end-user context when acting for a customer.
What authentication does AgentQL require?
The catalog lists an API key for AgentQL. Use Hosted Connect to authorize the intended account. Required permissions, provider app access and available connection methods depend on the integration.
How do I review sensitive AgentQL actions?
Limit enabled actions, scope credentials to the intended user and configure Human Gates for the operations that need review. A matching policy can pause a send, record change or other sensitive action for an approver before execution.
What limits or costs apply to AgentQL?
Weavz plan limits apply to the actions and resources you use. The external provider may also require an account, a paid plan, API credits or specific permissions, and may enforce its own rate limits. Check current Weavz pricing and the provider’s terms before rollout.
Connect AgentQL in minutes
Get 20,000 free action executions every month. No credit card required.