tinyfish_io_agentql_mcp

tinyfish_io_agentql_mcp

by tinyfish-io
A Model Context Protocol server that integrates AgentQL's data extraction capabilities for web scraping and structured data extraction.

AgentQL MCP Server: Web Data Extraction for AI Tools

Overview

The AgentQL MCP Server is a Model Context Protocol (MCP) implementation that integrates AgentQL's advanced data extraction capabilities. It enables AI tools like Claude, Cursor, and Windsurf to extract structured data from web pages using natural language prompts.

Features

Tools

  • extract-web-data: Extracts structured data from a given URL using a prompt that describes the data and fields to extract.

Installation

Install the Package

npm install -g agentql-mcp

Configure Claude

  1. Open Claude Desktop Settings via ⌘+,.
  2. Go to Developer > Edit Config.
  3. Add the agentql server configuration:
    json { "mcpServers": { "agentql": { "command": "npx", "args": ["-y", "agentql-mcp"], "env": { "AGENTQL_API_KEY": "YOUR_API_KEY" } } } }
  4. Restart the app.

Configure Cursor

  1. Open Cursor Settings > MCP > MCP Servers.
  2. Add a new MCP Server:
  3. Name: "agentql"
  4. Type: "command"
  5. Command: env AGENTQL_API_KEY=YOUR_API_KEY npx -y agentql-mcp

Configure Windsurf

  1. Open Windsurf: MCP Configuration Panel.
  2. Add the agentql server configuration:
    json { "mcpServers": { "agentql": { "command": "npx", "args": ["-y", "agentql-mcp"], "env": { "AGENTQL_API_KEY": "YOUR_API_KEY" } } } }

Validate MCP Integration

Test the integration by giving your agent a task like:

Extract the list of videos from the page https://www.youtube.com/results?search_query=agentql, every video should have a title, an author name, a number of views and a url to the video. Make sure to exclude ads items. Format this as a markdown table.

Development

Install Dependencies

npm install

Build the Server

npm run build

Development with Auto-Rebuild

npm run watch

Use Development Version

Replace the default config with:

{
  "mcpServers": {
    "agentql": {
      "command": "/path/to/agentql-mcp/dist/index.js",
      "env": {
        "AGENTQL_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Debugging

Use the MCP Inspector for debugging:

npm run inspector

About

The AgentQL MCP Server is designed to enhance AI tools with web data extraction capabilities, making it easier to integrate structured data into workflows.

Resources

Topics

  • AI, Web Scraping, MCP, Claude, Cursor, Windsurf, Playwright, LLM Tools

Contributors

Features & Capabilities

Categories
mcp_server model_context_protocol javascript web_scraping ai claude cursor windsurf api_integration docker playwright llm_tools agentql

Implementation Details

View on GitHub

Stats

0 Views
26 GitHub Stars

Repository Info

tinyfish-io Organization

Similar MCP Servers

continuedev_continue by continuedev
25049
cherryhq_cherry_studio by CherryHQ
21423
bytedance_ui_tars_desktop by bytedance
9300
2025© BestAI