agentql-mcp logo

agentql-mcpModel Context Protocol server that integrates AgentQL's data extraction capabilities.

(0)
Daniel NikulshynReviewed by Daniel Nikulshyn·Updated July 2026

Overview

AgentQL MCP Server is a Model Context Protocol (MCP) server that integrates AgentQL's data extraction capabilities. It allows users to extract structured data from web pages using a given URL and a prompt describing the actual data and its fields to extract. The server is designed to work with various applications that support MCP, such as Claude, VS Code, Cursor, and Windsurf. To use the server, users need to install it via npm, obtain an API key from the AgentQL Dev Portal, and configure it in their preferred app. The server supports one-click installation and manual configuration for different applications.

Key features

  • Extract web data using a given URL and prompt
  • Supports MCP protocol
  • Integrates with AgentQL's data extraction capabilities
  • Configurable for various applications

Pricing

Model
Free
Category
MCP Servers
Rating
No reviews yet

Use cases

Web Data Extraction

Extract structured data from web pages using a given URL and prompt, such as extracting a list of videos from a YouTube search results page.

Integration with Development Tools

Integrate AgentQL MCP Server with development tools like Claude, VS Code, Cursor, and Windsurf to enhance data extraction capabilities.

Pros & Cons

Pros

  • Integrates AgentQL's data extraction capabilities with MCP
  • Supports multiple applications, including Claude, VS Code, Cursor, and Windsurf
  • Allows for one-click installation and manual configuration

Cons

  • Requires an API key from the AgentQL Dev Portal
  • Needs to be configured in the user's preferred app

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Q&A

How do I make sure that my script waits enough for all the element to appear on the page?

AgentQL SDK provides the wait_for_page_ready_state() API to determine page readiness. This method waits for the page to be in a ready state and all the necessary network requests to be completed. However, there are some cases where the page might not be ready even after the method returns. This could be due to the dynamic nature of the page. In such cases, you can use the page.wait_for_timeout function to add a additional delay to your script. const { wrap } = require("agentql"); const { chromium } = require("playwright"); const QUERY = ` { related_videos[] { video_name video_rating } } `; async function main() { const browser = await chromium.launch({headless: false}); const page = await wrap(await browser.newPage()); await page.goto("https://www.youtube.com/watch?v=1ZvYrAaJOH4"); await page.waitForPageReadyState(); await page.waitForTimeout(5000); const response = await page.queryData(QUERY); console.log(`Related videos: \n${JSON.stringify(response, null, 2)}`); await browser.close(); } main();

Asked by Tunde Balogun · May 12, 2026

While writing AgentQL Script, how do I ensure the web page is loaded entirely?

It's currently not possible to programmatically define when a page has finished loading—a script may bring new information on to the page, as in the case of infinite scrolling or lazy loading images. You can use Playwright API to scroll the page up and down to load the more content. const { wrap } = require("agentql"); const { chromium } = require("playwright"); const QUERY = ` { comments[] } `; async function main() { const browser = await chromium.launch({headless: false}); const page = await wrap(await browser.newPage()); await page.goto("https://www.youtube.com/watch?v=1ZvYrAaJOH4"); for (let i = 0; i < 3; i++) { await page.mouse.wheel(delta_x=0, delta_y=1000); await page.waitForPageReadyState(); } await page.mouse.wheel(delta_x=0, delta_y=-3000); const response = await page.queryData(QUERY); console.log(`Video comments: \n${JSON.stringify(response, null, 2)}`); await browser.close(); } main();

Asked by Liam O’Connor · Apr 1, 2026

How do I specify the format of data returned by AgentQL?

Since the release of 0.4.7 version, AgentQL supports providing context to query in the following way: { products[] { price(Format the output as a numerical value only, no dollar sign) name(Format the output with the following prefix: amazon_) } } As you can see, by providing formatting instructions as a context into the query, you could instruct AgentQL to return the expected data format.

Asked by Xander de Vries · Mar 13, 2026

Ask a question

MCP Servers alternatives