AgentQL
AgentQL
Use your AgentQL credentials to extract data from webpages
AgentX allows you connect AI agents with thousands of the most popular apps through MCP, so you can automate your AI workflow and have more time for what matters most — no code required.
Installation
Run AgentQL MCP server on AgentX without a single line of code.
Check out our docsOr run AgentQL MCP server on your terminal:
npx -y agentql-mcpRun this command to start the AgentQL MCP server.
View on GitHubRequired Environment Variables
Make sure to set these environment variables before running the server.
View full documentationLinks
Server Information
Documentation
View on GitHubAgentQL MCP Server
This is a Model Context Protocol (MCP) server that integrates AgentQL's data extraction capabilities.
Features
Tools
extract-web-data- extract structured data from a given 'url', using 'prompt' as a description of actual data and its fields to extract.
Installation
To use AgentQL MCP Server to extract data from web pages, you need to install it via npm, get an API key from our Dev Portal, and configure it in your favorite app that supports MCP.
Install the package
npm install -g agentql-mcp
Configure Claude
- Open Claude Desktop Settings via
⌘+,(don't confuse with Claude Account Settings) - Go to Developer sidebar section
- Click Edit Config and open
claude_desktop_config.jsonfile - Add
agentqlserver insidemcpServersdictionary in the config file - Restart the app
{
"mcpServers": {
"agentql": {
"command": "npx",
"args": ["-y", "agentql-mcp"],
"env": {
"AGENTQL_API_KEY": "YOUR_API_KEY"
}
}
}
}
Read more about MCP configuration in Claude here.
Configure VS Code
For one-click installation, click one of the install buttons below:
Manual Installation
Click the install buttons at the top of this section for the quickest installation method. For manual installation, follow these steps:
Add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).
{
"mcp": {
"inputs": [
{
"type": "promptString",
"id": "apiKey",
"description": "AgentQL API Key",
"password": true
}
],
"servers": {
"agentql": {
"command": "npx",
"args": ["-y", "agentql-mcp"],
"env": {
"AGENTQL_API_KEY": "${input:apiKey}"
}
}
}
}
}
Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.
{
"inputs": [
{
"type": "promptString",
"id": "apiKey",
"description": "AgentQL API Key",
"password": true
}
],
"servers": {
"agentql": {
"command": "npx",
"args": ["-y", "agentql-mcp"],
"env": {
"AGENTQL_API_KEY": "${input:apiKey}"
}
}
}
}
Configure Cursor
- Open Cursor Settings
- Go to MCP > MCP Servers
- Click + Add new MCP Server
- Enter the following:
- Name: "agentql" (or your preferred name)
- Type: "command"
- Command:
env AGENTQL_API_KEY=YOUR_API_KEY npx -y agentql-mcp
Read more about MCP configuration in Cursor here.
Configure Windsurf
- Open Windsurf: MCP Configuration Panel
- Click Add custom server+
- Alternatively you can open
~/.codeium/windsurf/mcp_config.jsondirectly - Add
agentqlserver insidemcpServersdictionary in the config file
{
"mcpServers": {
"agentql": {
"command": "npx",
"args": ["-y", "agentql-mcp"],
"env": {
"AGENTQL_API_KEY": "YOUR_API_KEY"
}
}
}
}
Read more about MCP configuration in Windsurf here.
Validate MCP integration
Give your agent a task that will require extracting data from the web. For example:
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.
[!TIP] In case your agent complains that it can't open urls or load content from the web instead of using AgentQL, try adding "use tools" or "use agentql tool" hint.
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
If you want to try out development version, you can use the following config instead of the default one:
{
"mcpServers": {
"agentql": {
"command": "/path/to/agentql-mcp/dist/index.js",
"env": {
"AGENTQL_API_KEY": "YOUR_API_KEY"
}
}
}
}
[!NOTE] Don't forget to remove the default AgentQL MCP server config to not confuse Claude with two similar servers.
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Explore More MCP Servers
Discover other popular Model Context Protocol servers.
YouTube DLP
Lets your AI interact with YouTube videos - search videoes, extract video information, subtitles, and top comments without downloading.
Command:
uvx youtube-dlp-serverYahoo Finance
Lets your AI agents interact with Yahoo Finance - get comprehensive stock market data, news, financials, and more.
Command:
uvx yahoo-finance-serverApollo io
Enabling AI agents to interact with Apollo.io data for people and organization search and enrichment.
Command:
npx -y @agentx-ai/apollo-io-mcp-serverActiveCampaign
Intelligent marketing automation platform
Command:
uvx ac-mcp-serverGoogle Maps
Use Google Maps knowledge directly in your agent by providing your API key.
Command:
npx -y @modelcontextprotocol/server-google-mapsNotion
MCP Server for the Notion API, enabling LLM to interact with Notion workspaces.
Server:
https://mcp.notion.com/ssePerplexity
Integrate Perplexity as a search engine for your agent.
Command:
npx -y server-perplexity-askAirTable
Read and write access to Airtable databases, with schema inspection.
Command:
npx -y airtable-mcp-serverSalesforce
A (MCP) server implementation for Salesforce integration, allowing AI to interact with Salesforce data through SOQL queries and SOSL searches.
Command:
uvx --from mcp-salesforce-connector ...Mailchimp
Access to Mailchimp's Marketing API for comprehensive email marketing data retrieval.
Command:
npx -y @agentx-ai/mailchimp-mcp-serverNASA
A Model Context Protocol (MCP) server for NASA APIs, providing a standardized interface for AI models to interact with NASA's vast array of data sources.
Command:
npx -y @programcomputer/nasa-mcp-server@latest ...MongoDB
Use your MongoDB database to store and retrieve data.
Command:
npx -y mcp-mongo-server ...AgentX | One-stop AI Agent build platform.
Book a demoTUTORIALS
- How to build an AI agent
- How to setup Lead Gen
- How to deploy to the websites
- How to deploy to the Slack workspace
- How to deploy to the Discord server
- How to deploy to WhatsApp Business
- How to add a MCP to your AI Agent
- Lead Generation with HubSpot CRM
- Lead Generation with Wix CRM
- Lead Generation with Zapier webhook
- Zapier Integration Overview
- How to Fully Rebrand Your AI Agent
- How to make AI agent that handles Google Calendar
- How to Build AI Agent Workforce
- Connect AI Agent to Calendly
- How to connect iCal to your AI Agent
- How to Automate Tasks
- Deep Image Understanding
- Connect Google Sheets to Your Agent
- How to create a custom tool in AgentX
- How to setup Custom Branding for E-mails
- How to Connect AgentX Lead Gen to ActiveCampaign CRM
PRODUCT
© 2026 AgentX Inc