AgentQL Data Extraction

v1.0.1Browser Automationstable

A server that provides AgentQL's data extraction capabilities enabling AI agents to get structured data from unstructured web

agentagentqlaiaiagentclaude
Share:
171
Stars
0
Downloads
0
Weekly
0/5

What is AgentQL Data Extraction?

AgentQL Data Extraction is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to server that provides agentql's data extraction capabilities enabling ai agents to get structured data from unstructured web

A server that provides AgentQL's data extraction capabilities enabling AI agents to get structured data from unstructured web

This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A server that provides AgentQL's data extraction capabilitie

Use Cases

Extract structured data from web pages
Unstructured web data parsing
Agent-powered web scraping
tinyfish-io

Maintainer

LicenseMIT License
Languagejavascript
Versionv1.0.1
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y agentql-mcp

Manual Installation

npx -y agentql-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use AgentQL Data Extraction

The AgentQL MCP server gives AI agents the ability to extract structured data from any web page by describing what they want in plain language rather than writing CSS selectors or XPath. It exposes a single `extract-web-data` tool that accepts a URL and a natural language description of the fields to extract, then returns clean, structured data powered by AgentQL's cloud API. This is particularly useful for agents that need to pull product listings, search results, pricing, or any web content without dealing with brittle scraper code.

Prerequisites

  • Node.js 18+ installed (required to run `npx`)
  • An AgentQL API key from the AgentQL Developer Portal at https://dev.agentql.com
  • An MCP-compatible client such as Claude Desktop, Cursor, Windsurf, or VS Code
1

Obtain an AgentQL API key

Sign up at https://dev.agentql.com and create an API key from the Developer Portal dashboard. Keep this key available for the next step.

2

Add the server to your MCP client config

Add the AgentQL entry to your `claude_desktop_config.json` (or equivalent for your client) under `mcpServers`. Set `AGENTQL_API_KEY` to your key from the previous step.

3

Restart your MCP client

Restart Claude Desktop (or your chosen client) to load the new server configuration. The AgentQL server will be launched automatically via npx.

4

Test with a simple extraction

Ask your AI client to extract data from a public web page to verify the tool is working. You should get back a structured result without writing any code.

5

Debug with the MCP Inspector (optional)

If the tool is not being called, use the MCP Inspector to test it directly or provide a hint in your prompt like 'use the agentql tool'.

npx @modelcontextprotocol/inspector npx -y agentql-mcp

AgentQL Data Extraction Examples

Client configuration

Claude Desktop config block that launches the AgentQL MCP server via npx with your API key.

{
  "mcpServers": {
    "agentql": {
      "command": "npx",
      "args": ["-y", "agentql-mcp"],
      "env": {
        "AGENTQL_API_KEY": "YOUR_AGENTQL_API_KEY"
      }
    }
  }
}

Prompts to try

Example extraction tasks you can ask once the AgentQL MCP server is connected.

- "Extract the list of videos from https://www.youtube.com/results?search_query=agentql — each video should have title, author, view count, and URL. Format as a markdown table."
- "Get all product names and prices from https://news.ycombinator.com — return title, points, and comment count for the top 10 stories"
- "Extract the job listings from a careers page: title, location, and department for each open role"
- "Pull the speaker names and talk titles from a conference schedule page"
- "Get the latest 5 GitHub releases from a repository's releases page including version number and release date"

Troubleshooting AgentQL Data Extraction

The AI ignores AgentQL and tries to fetch the page itself

Add an explicit hint in your prompt such as 'use the agentql tool' or 'use tools to extract data'. Some clients need encouragement to prefer MCP tools over built-in browsing capabilities.

API key errors or 401 Unauthorized responses

Verify `AGENTQL_API_KEY` is set correctly in your MCP config `env` block and that the key is active in your AgentQL Dev Portal at https://dev.agentql.com. Keys may need to be regenerated if they expire.

Extraction returns incomplete or empty results

The page may require JavaScript rendering or authentication. Try describing the fields you want more specifically in your prompt. Pages behind logins or CAPTCHAs may not be accessible. Use the MCP Inspector (`npx @modelcontextprotocol/inspector npx -y agentql-mcp`) to test the tool directly.

Frequently Asked Questions about AgentQL Data Extraction

What is AgentQL Data Extraction?

AgentQL Data Extraction is a Model Context Protocol (MCP) server that server that provides agentql's data extraction capabilities enabling ai agents to get structured data from unstructured web It connects AI assistants to external tools and data sources through a standardized interface.

How do I install AgentQL Data Extraction?

Install via npm with the command: npx -y agentql-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with AgentQL Data Extraction?

AgentQL Data Extraction works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is AgentQL Data Extraction free to use?

Yes, AgentQL Data Extraction is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Browser Automation MCP Servers

Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "agentql-mcp-server": { "command": "npx", "args": ["-y", "agentql-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use AgentQL Data Extraction?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides