Server profile

AgentQL MCP Server

AgentQL MCP Server extracts structured JSON from a web page using a natural-language description of the desired fields. It provides one focused extraction tool for MCP assistants.

Server facts

AgentQL MCP Server

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
181
Last commit
Data as of

Tags

  • Agentql
  • Natural Language
  • Nodejs
  • Structured Data
  • Web Extraction

Overview

AgentQL MCP Server exposes AgentQL web-data extraction through a single MCP tool. The caller supplies a page URL and a natural-language prompt describing the information and fields to collect. The result is structured JSON rather than an unprocessed page dump. This focus makes the server a small integration for assistants that need data from a page in a defined shape. The README demonstrates a video-results extraction task asking for titles, creators, view counts, and video links while excluding advertising entries; that is an example request, not a separate video-specific tool.

Installation uses the agentql-mcp npm package, and the client configuration starts it through npx. An AgentQL API key from the developer portal is required and passed as AGENTQL_API_KEY. The README provides configurations for Claude Desktop, VS Code, Cursor, and Windsurf, including an input prompt for the key in VS Code. It also documents a built local version for development and recommends removing duplicate server configurations when testing that version. MCP Inspector is available through a package script for debugging stdio communication. The supplied material does not specify pricing, service quotas, authentication flows for target websites, or additional browsing actions. Selection should therefore rest on the documented URL-plus-description extraction interface, not assumptions about a general-purpose browser automation suite.

Install & configure

Requirements

  • Node.js with npm / npx
  • AgentQL API key
  • An MCP-compatible host
Documented launch / install command
npx -y agentql-mcp

The README also documents npm install -g agentql-mcp. Restart the host after adding its configuration. Development builds should replace, rather than duplicate, the default server entry.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "agentql-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agentql-mcp"
      ],
      "env": {
        "AGENTQL_API_KEY": "<API key from the AgentQL developer portal>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "agentql-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agentql-mcp"
      ],
      "env": {
        "AGENTQL_API_KEY": "<API key from the AgentQL developer portal>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "agentql-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agentql-mcp"
      ],
      "env": {
        "AGENTQL_API_KEY": "<API key from the AgentQL developer portal>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "agentql-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agentql-mcp"
      ],
      "env": {
        "AGENTQL_API_KEY": "<API key from the AgentQL developer portal>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "agentql-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agentql-mcp"
      ],
      "env": {
        "AGENTQL_API_KEY": "<API key from the AgentQL developer portal>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
extract-web-dataExtract JSON fields from a page URL using a natural-language description.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Extract named fields from a page into JSON.
  • Collect video-result metadata as illustrated in the README.
  • Bring structured page data into an assistant report.
  • Use the same extraction tool across supported MCP hosts.

Strengths

  • One focused tool with URL and natural-language inputs.
  • Returns structured JSON instead of requiring raw-page interpretation.
  • Documents setup for several common MCP clients.

Limitations

  • Requires an AgentQL API key.
  • Only one extraction tool is documented.
  • Pricing and usage limits are not stated in the README.

Frequently asked questions

The tool accepts a page URL and a prompt describing the desired data and fields.

The supplied tool facts identify structured JSON output.

The README directs users to the AgentQL developer portal at https://dev.agentql.com.

No. The supplied README and tool list describe only extract-web-data.

The README suggests explicitly asking the assistant to use tools or the AgentQL tool.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

MCP for Unity

Games & 3D

MCP for Unity links AI assistants to the Unity Editor for scene work, asset management, script editing, testing, and builds. It targets game developers who want to direct editor workflows through natural language.

Firecrawl MCP Server

Search & Web Data

Firecrawl MCP connects AI agents to web search, scraping, crawling, and live browser interaction. It offers hosted access or a local server for collecting structured web context and running research tasks.

Tavily MCP Server

Search & Web Data

Tavily MCP Server connects AI clients to web search, page extraction, site mapping, and crawling. Run it locally with an API key or connect to the hosted service using API-key or OAuth authentication.

Exa MCP Server

Search & Web Data

Exa MCP Server gives AI assistants web search and readable page retrieval, with optional advanced search and agent research tools. It supports hosted connections and a local npm package for research and coding context.

Perplexity API Platform MCP Server

Search & Web Data

The Perplexity API Platform MCP Server gives assistants web search, conversational answers, research, and reasoning tools. It connects to Perplexity’s Search API and Sonar models through local stdio or an HTTP deployment.

ArXiv MCP Server

Search & Web Data

Search arXiv, download papers, and read their contents through an AI assistant. Local storage and research prompts support repeatable literature review and paper analysis.

Bright Data Web MCP

Search & Web Data

Give AI assistants live web search, page extraction, and optional browser automation through Bright Data. Tool groups also provide structured datasets, package information, and AI brand-visibility queries.

DuckDuckGo Search MCP Server

Search & Web Data

Give MCP assistants DuckDuckGo search and webpage text retrieval. It suits research workflows that need regional results, readable page content, and configurable filtering.