Skip to main content
Glama

Servidor MCP de AgentQL

Este es un servidor de Protocolo de Contexto de Modelo (MCP) que integra las capacidades de extracción de datos de AgentQL .

Características

Herramientas

  • extract-web-data : extrae datos estructurados de una 'URL' determinada, utilizando 'prompt' como descripción de los datos reales y sus campos a extraer.

Related MCP server: Fetcher MCP

Instalación

Para utilizar AgentQL MCP Server para extraer datos de páginas web, debe instalarlo a través de npm, obtener una clave API de nuestro Portal de desarrolladores y configurarlo en su aplicación favorita que admita MCP.

Instalar el paquete

npm install -g agentql-mcp

Configurar Claude

  • Abra la configuración de escritorio de Claude mediante ⌘ + , (no confunda con la configuración de la cuenta de Claude)

  • Vaya a la sección de la barra lateral del desarrollador

  • Haga clic en Editar configuración y abra el archivo claude_desktop_config.json

  • Agregue el servidor agentql dentro del diccionario mcpServers en el archivo de configuración

  • Reiniciar la aplicación

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

Lea más sobre la configuración de MCP en Claude aquí .

Configurar cursor

  • Abrir configuración del cursor

  • Vaya a MCP > Servidores MCP

  • Haga clic en + Agregar nuevo servidor MCP

  • Introduzca lo siguiente:

    • Nombre: "agentql" (o su nombre preferido)

    • Tipo: "comando"

    • Comando: env AGENTQL_API_KEY=YOUR_API_KEY npx -y agentql-mcp

Lea más sobre la configuración de MCP en Cursor aquí .

Configurar Windsurf

  • Open Windsurf: Panel de configuración MCP

  • Haga clic en Agregar servidor personalizado+

  • Alternativamente, puede abrir ~/.codeium/windsurf/mcp_config.json directamente

  • Agregue el servidor agentql dentro del diccionario mcpServers en el archivo de configuración

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

Lea más sobre la configuración de MCP en Windsurf aquí .

Validar la integración de MCP

Asigna a tu agente una tarea que requiera extraer datos de la web. Por ejemplo:

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] En caso de que su agente se queje de que no puede abrir URL o cargar contenido de la web en lugar de usar AgentQL, intente agregar la sugerencia "usar herramientas" o "usar herramienta agentql".

Desarrollo

Instalar dependencias:

npm install

Construir el servidor:

npm run build

Para desarrollo con reconstrucción automática:

npm run watch

Si desea probar la versión de desarrollo, puede utilizar la siguiente configuración en lugar de la predeterminada:

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

[!NOTA] No olvides eliminar la configuración del servidor MCP de AgentQL predeterminada para no confundir a Claude con dos servidores similares.

Depuración

Dado que los servidores MCP se comunican a través de stdio, la depuración puede ser complicada. Recomendamos usar el Inspector MCP , disponible como script de paquete:

npm run inspector

El Inspector proporcionará una URL para acceder a las herramientas de depuración en su navegador.

Available Tools

1 tool
extract-web-dataA

Extracts structured data as JSON from a web page given a URL using a Natural Language description of the data.

ParametersJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL of the public webpage to extract data from
promptYesNatural Language description of the data to extract from the page

TDQS

A3.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. Describes core function but omits important behavioral traits like rate limits, authentication requirements, handling of dynamic content, or error scenarios.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single concise sentence that is front-loaded and contains only essential information. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Mentions output format (JSON) but lacks details on return structure, error handling, or limitations like URL restrictions or page complexity. Adequate for a simple tool but incomplete for production use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions. The description reinforces the 'prompt' parameter's nature but adds no new meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states verb (Extracts), resource (structured data as JSON from web page), and method (Natural Language description). Specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implicitly indicates use when needing structured data from a URL via NL description. No siblings to differentiate, but lacks explicit when-not-to-use or alternative methods.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • Addedextract-web-data
  2. 1 tool updatev1.0.0
    • Removedextract-web-data
  3. 1 tool update
    • First observedextract-web-data

TDQS

A3.6/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no risk of confusion between tools, so disambiguation is perfect.

Naming Consistency5/5

The single tool name 'extract-web-data' follows a clear verb_noun pattern, and consistency is trivially maintained.

Tool Count2/5

A single tool is too few for a web scraping server, which typically requires tools for different actions (e.g., listing, configuring) or handling multiple extraction strategies.

Completeness2/5

The server only provides extraction via natural language, missing common features like pagination, multiple output formats, or error handling, leaving significant gaps for agents.

Maintenance

ActivityActive
ResponsivenessUnresponsive

Related MCP Connectors

Related MCP Servers

  • A
    license
    C
    quality
    D
    maintenance
    A server that provides web scraping and intelligent content searching capabilities using the Firecrawl API, enabling AI agents to extract structured data from websites and perform content searches.
    5
    3
    MIT
  • -
    license
    C
    quality
    Not graded
    maintenance
    A server that allows fetching web page content using Playwright headless browser with AI-powered capabilities for efficient information extraction.
    2
    4,375 npm
    7
    -