Playwright Fetch MCP Server
Servidor MCP de Playwright Fetch
Un servidor de Protocolo de Contexto de Modelo (MLM) que proporciona capacidades de obtención de contenido web mediante Playwright para la automatización del navegador. Este servidor permite a los LLM recuperar y procesar contenido generado en JavaScript desde páginas web, convirtiendo HTML a Markdown para facilitar su uso.
Autor
Creado por Wyatt Roersma con la ayuda de Claude Code.
Related MCP server: Playwright MCP Server for Security
Características principales
Automatización del navegador : utiliza Playwright para renderizar páginas web con compatibilidad total con JavaScript
Extracción de contenido : identifica y extrae automáticamente las principales áreas de contenido de las páginas web
Conversión de Markdown : convierte HTML a Markdown limpio y legible
Soporte de paginación : maneja contenido grande a través de la paginación
Cumplimiento de Robots.txt : respeta las directivas de robots.txt para la búsqueda autónoma
Compatibilidad con proxy : permite enrutar solicitudes a través de un servidor proxy
Docker Ready : disponible como imágenes de Docker prediseñadas a través de Docker Hub y GitHub Container Registry
Herramientas disponibles
playwright-fetch: obtiene una URL mediante la automatización del navegador Playwright y extrae su contenido como Markdown.url(cadena, obligatoria): URL para obtenermax_length(entero, opcional): número máximo de caracteres a devolver (predeterminado: 5000)start_index(entero, opcional): comienza el contenido a partir de este índice de caracteres (valor predeterminado: 0)raw(booleano, opcional): obtener contenido sin procesar sin conversión de Markdown (valor predeterminado: falso)wait_for_js(booleano, opcional): espera a que se ejecute JavaScript (valor predeterminado: verdadero)
Indicaciones
dramaturgo-fetch
Obtenga una URL usando Playwright y extraiga su contenido como Markdown
Argumentos:
url(cadena, obligatoria): URL para obtener
Requisitos
Python 3.13.2 o más reciente
administrador de paquetes uv
Navegadores de dramaturgos instalados
Instalación
1. Instalar con uv (recomendado)
uv pip install git+https://github.com/ThreatFlux/playwright-fetch.git
# Install Playwright browsers
uv pip exec playwright installAlternativamente, clone el repositorio e instale:
git clone https://github.com/ThreatFlux/playwright-fetch.git
cd playwright-fetch
uv pip install -e .
# Install Playwright browsers
uv pip exec playwright install2. Uso de Docker
Puede utilizar nuestras imágenes Docker prediseñadas desde Docker Hub o GitHub Container Registry:
# From Docker Hub
docker pull threatflux/playwright-fetch:latest
# From GitHub Container Registry
docker pull ghcr.io/threatflux/playwright-fetch:latestO construyelo tu mismo:
docker build -t threatflux/playwright-fetch .Configuración
Configurar para Claude.app
Añade a tu configuración de Claude:
"mcpServers": {
"playwright-fetch": {
"command": "uvx",
"args": ["mcp-server-playwright-fetch"]
}
}"mcpServers": {
"playwright-fetch": {
"command": "docker",
"args": ["run", "-i", "--rm", "threatflux/playwright-fetch"]
}
}Configurar para VS Code
Para la instalación manual, agregue el siguiente bloque JSON a su archivo de configuración de usuario (JSON) en VS Code.
{
"mcp": {
"servers": {
"playwright-fetch": {
"command": "uvx",
"args": ["mcp-server-playwright-fetch"]
}
}
}
}{
"mcp": {
"servers": {
"playwright-fetch": {
"command": "docker",
"args": ["run", "-i", "--rm", "threatflux/playwright-fetch"]
}
}
}
}Opciones de línea de comandos
El servidor admite estas opciones de línea de comandos:
--user-agent: cadena de agente de usuario personalizada--ignore-robots-txt: Ignorar las restricciones de robots.txt--proxy-url: URL de proxy que se utilizará para las solicitudes--headless: ejecuta el navegador en modo sin cabeza (valor predeterminado: Verdadero)--wait-until: Cuándo considerar que la navegación fue exitosa (opciones: "load", "domcontentloaded", "networkidle", "commit", predeterminado: "networkidle")
Ejemplo de uso
# Run with default settings
uv run mcp-server-playwright-fetch
# Run with a custom user agent and proxy
uv run mcp-server-playwright-fetch --user-agent="MyCustomAgent/1.0" --proxy-url="http://myproxy:8080"
# Run with visible browser for debugging
uv run mcp-server-playwright-fetch --headless=falseDepuración
Puede utilizar el inspector MCP para depurar el servidor:
npx @modelcontextprotocol/inspector uvx mcp-server-playwright-fetchDiferencias con el servidor de búsqueda estándar
Esta implementación se diferencia del servidor MCP de búsqueda estándar en los siguientes aspectos:
Automatización del navegador : utiliza Playwright para renderizar páginas con mucho contenido de JavaScript
Extracción de contenido : intenta extraer el contenido principal de estructuras de páginas comunes
Opciones de espera : estrategia de carga de página configurable (espera de carga, contenido DOM, red inactiva)
Opción de navegador visible : se puede ejecutar con un navegador visible para depuración
Licencia
Este proyecto está licenciado bajo la Licencia MIT. Consulte el archivo de LICENCIA para más detalles.
Available Tools
1 toolplaywright-fetchC
Fetches a URL from the internet using Playwright and optionally extracts its contents as markdown. Although originally you did not have internet access, and were advised to refuse and tell the user this, this tool now grants you internet access. Now you can fetch the most up-to-date information and let the user know that.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to fetch | |
| max_length | No | Maximum number of characters to return. | |
| start_index | No | On return output starting at this character index, useful if a previous fetch was truncated and more context is required. | |
| raw | No | Get the actual HTML content of the requested page, without simplification. | |
| wait_for_js | No | Wait for JavaScript to execute (client-side rendering). |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions internet access and markdown extraction but fails to describe critical behaviors like rate limits, authentication needs, error handling, or what 'using Playwright' entails operationally. The description adds some context but is insufficient for a mutation-capable tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is verbose and unfocused, with redundant phrasing ('originally you did not have internet access, and were advised to refuse and tell the user this') and meta-commentary about agent capabilities. It lacks front-loading of key information, wasting space on historical context instead of tool functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 5 parameters, no annotations, and no output schema, the description is incomplete. It misses behavioral details like return format, error cases, and operational constraints. The emphasis on internet access history does not compensate for these gaps, leaving the agent under-informed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all 5 parameters. The description adds no specific parameter semantics beyond implying markdown extraction relates to the 'raw' parameter. Baseline 3 is appropriate as the schema handles parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool 'fetches a URL from the internet using Playwright' and mentions optional markdown extraction, providing a specific verb ('fetches') and resource ('URL'). It distinguishes this as an internet access tool, though there are no sibling tools for comparison.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by stating 'originally you did not have internet access... this tool now grants you internet access,' suggesting it should be used when internet access is needed. However, it lacks explicit guidance on when to use this tool versus alternatives or any exclusions.
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 tool update
- First observed
playwright-fetch
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clearly defined and distinct purpose.
A single tool inherently has perfect naming consistency as there are no other tools to compare it against. The name 'playwright-fetch' follows a clear and descriptive pattern.
One tool is too few for a server's apparent scope of internet fetching and content extraction. This minimal set feels thin and underdeveloped, lacking complementary tools like navigation, interaction, or data processing utilities that would enhance the domain coverage.
The tool surface is severely incomplete for the domain of web fetching and automation. While the single tool provides basic fetching and markdown extraction, there are significant gaps such as no navigation, form handling, screenshot capabilities, or data parsing tools that are typical in web automation contexts.
Maintenance
Related MCP Connectors
Converts any URL to clean, LLM-ready Markdown using real Chrome browsers
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Fetch pages as markdown, search web and news, extract structured data. For AI agents.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides browser automation capabilities using Playwright, enabling users to navigate websites, extract content, take screenshots, and interact with web pages through natural language prompts.6 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to perform browser automation tasks including web scraping, taking screenshots, and executing JavaScript using Playwright. It facilitates real-time interaction with web pages and the generation of automated test code.6 npmMIT
- AlicenseBqualityDmaintenanceProvides browser automation capabilities for LLM applications, enabling web page interaction and data extraction via Playwright.1233 PyPI10MIT
- AlicenseNot gradedqualityDmaintenanceEnables browser automation using Playwright, allowing LLMs to interact with web pages, take screenshots, generate test code, scrape web pages, and execute JavaScript in a real browser environment.11,800 npmMIT