AgentQL MCP ServerFeatured
@tinyfish-io
About AgentQL MCP Server
Model Context Protocol server that integrates AgentQL's data extraction capabilities.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"agentql": {
"command": "npx",
"args": [
"-y",
"agentql-mcp"
],
"env": {
"AGENTQL_API_KEY": "YOUR_API_KEY"
}
}
}
}Tools
1Extracts structured data as JSON from a web page given a URL using a Natural Language description of the data.
Overview
What is AgentQL MCP Server?
AgentQL MCP Server is a Model Context Protocol (MCP) server that integrates AgentQL’s data extraction capabilities, allowing AI agents to extract structured data from web pages via a single tool. It is designed for developers using MCP‑compatible apps like Claude, VS Code, Cursor, or Windsurf.
How to use AgentQL MCP Server?
Install the npm package globally (npm install -g agentql-mcp), obtain an API key from the AgentQL Dev Portal, then configure the server in your MCP‑enabled application’s settings (e.g., claude_desktop_config.json). Use the extract-web-data tool with a URL and a prompt describing the data fields you want.
Key features of AgentQL MCP Server
extract-web-datatool to extract structured data from any URL.- Uses natural language prompts to describe desired fields.
- Works with Claude, VS Code, Cursor, and Windsurf.
- Requires only an AgentQL API key for authentication.
- Installed via npm (global or via
npx).
Use cases of AgentQL MCP Server
- Extract a list of videos (title, author, views, URL) from a YouTube search results page.
- Pull product details (name, price, rating) from an e‑commerce site.
- Retrieve contact information or job listings from a company website.
- Generate structured data reports from any public web page.
FAQ from AgentQL MCP Server
What is the extract-web-data tool?
It is a single MCP tool that takes a url and a prompt describing the data fields to extract, then returns structured JSON from the page.
What runtime dependencies are required?
The server runs on Node.js and requires an internet connection to call the AgentQL API. An API key from dev.agentql.com is mandatory.
How is authentication handled?
Authentication is configured via the AGENTQL_API_KEY environment variable set in the MCP server configuration (or passed inline in Cursor).
Where does the extracted data come from?
AgentQL MCP Server uses the AgentQL cloud API to analyze web pages; the server itself does not store data – it relays the requested extraction to AgentQL.
What transport does the server use?
It communicates over standard input/output (stdio) as a standard MCP server, enabling integration with any MCP‑compatible client.
Frequently asked questions
What is the `extract-web-data` tool?
It is a single MCP tool that takes a `url` and a `prompt` describing the data fields to extract, then returns structured JSON from the page.
What runtime dependencies are required?
The server runs on Node.js and requires an internet connection to call the AgentQL API. An API key from dev.agentql.com is mandatory.
How is authentication handled?
Authentication is configured via the `AGENTQL_API_KEY` environment variable set in the MCP server configuration (or passed inline in Cursor).
Where does the extracted data come from?
AgentQL MCP Server uses the AgentQL cloud API to analyze web pages; the server itself does not store data – it relays the requested extraction to AgentQL.
What transport does the server use?
It communicates over standard input/output (stdio) as a standard MCP server, enabling integration with any MCP‑compatible client.
Basic information
More Other MCP servers
Codelf
unbugA search tool helps dev to solve the naming things problem.
Mobile Mcp
mobile-nextModel Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
ACI: Open-Source Infra to Power Unified MCP Servers
aipotheosis-labsACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
Comments