Servidor MCP para Rendex: captura capturas de pantalla y archivos PDF de cualquier página web mediante agentes de IA utilizando el Protocolo de Contexto de Modelo (Model Context Protocol).
Añade esto a la configuración de tu cliente MCP:
{
"mcpServers": {
"rendex": {
"command": "npx",
"args": ["-y", "@copperline/rendex-mcp"],
"env": {
"RENDEX_API_KEY": "your-api-key"
}
}
}
}Dónde añadir esto:
Cliente | Ubicación de la configuración |
Claude Desktop |
|
Cursor |
|
Windsurf | Ajustes > Servidores MCP |
Añade un archivo .mcp.json a la raíz de tu proyecto con la misma configuración anterior. Luego reinicia Claude Code.
Importante: Añade
.mcp.jsona tu.gitignore: contiene tu clave API.
Conéctate directamente, no se requiere instalación (solo para Claude Desktop):
{
"mcpServers": {
"rendex": {
"url": "https://mcp.rendex.dev/mcp",
"headers": {
"Authorization": "Bearer your-api-key"
}
}
}
}Related MCP server: Screenshot API
rendex_screenshotCaptura una captura de pantalla o un PDF de cualquier página web o HTML sin procesar.
"Take a screenshot of https://example.com"
"Capture the full page of https://news.ycombinator.com in dark mode"
"Generate a PDF of https://github.com with A4 page size"
"Capture https://amazon.de as seen from Germany"
"Render this HTML invoice as a PDF"Parámetros:
Parámetro | Tipo | Predeterminado | Descripción | |||
| string | requerido* | URL de la página web a capturar. Excluyente con | |||
| string | — | HTML sin procesar a renderizar. Excluyente con | |||
|
|
|
|
|
| Formato de salida |
| boolean |
| Capturar página completa desplazable | |||
| boolean |
| Emular esquema de color oscuro | |||
| number |
| Ancho del viewport (320-3840) | |||
| number |
| Alto del viewport (240-2160) | |||
| number |
| Calidad de imagen 1-100 (solo JPEG/WebP, predeterminado 80) | |||
| number |
| Esperar ms antes de la captura | |||
| boolean |
| Bloquear anuncios y rastreadores | |||
| string[] | — | Bloquear tipos de recursos: | |||
| number |
| Relación de píxeles del dispositivo (1-3). 2× Retina por defecto | |||
| number |
| Segundos máximos de espera para la carga de la página (5-60) | |||
| string |
| Preparación de la página: | |||
| string | — | Selector CSS a esperar antes de la captura | |||
| boolean |
| Devolver renderizado parcial en caso de tiempo de espera en lugar de fallar | |||
| string | — | Selector CSS del elemento a capturar en lugar de la página completa | |||
| string | — | CSS personalizado a inyectar antes de la captura (máx. 50KB) | |||
| string | — | JavaScript personalizado a ejecutar antes de la captura (máx. 50KB) | |||
| array | — | Cookies a establecer para capturas autenticadas (máx. 50) | |||
| object | — | Cabeceras HTTP personalizadas para la solicitud de la página | |||
| string | — | Sobrescribir la cadena de agente de usuario del navegador | |||
| string | — | Tamaño de página PDF: | |||
| boolean | — | Orientación horizontal del PDF | |||
| boolean |
| Imprimir fondo en PDF | |||
| number |
| Factor de escala del PDF (0.1-2) | |||
| object | — | Márgenes del PDF: | |||
| string | — | Código de país ISO para captura con segmentación geográfica (Pro/Enterprise) | |||
| string | — | Ciudad para segmentación geográfica (requiere | |||
| string | — | Estado para segmentación geográfica (requiere | |||
| boolean | — | Procesar de forma asíncrona (devuelve ID de trabajo) | |||
| string | — | URL para recibir la devolución de llamada cuando se complete la captura asíncrona | |||
| number | — | Segundos para almacenar el resultado en caché (3600-2592000) |
Obtén tu clave API en rendex.dev.
Establece la variable de entorno RENDEX_API_KEY en la configuración de tu cliente MCP.
Plan | Llamadas/Mes | Tasa |
Free | 500 | 10/min |
Starter | 10,000 | 60/min |
Pro | 100,000 | 300/min |
Enterprise | Personalizado | 1,000/min |
MIT — Copperline Labs LLC
Extract clean reader-mode content from any webpage as Markdown, JSON, or HTML. Runs the same Chromium render pass as a screenshot, so it captures content after JavaScript runs — handles SPAs that fetch-only readers miss. Strips nav, ads, and boilerplate, returning the article body plus title, byline, and excerpt. Great for feeding page content to an LLM, summarization, or RAG ingestion.
Inputs: url (required), extractFormat, waitUntil, timeout, +4 more.
Render a URL, raw HTML, or Markdown and get back a signed, hosted, edge-cached image URL instead of the bytes — ideal for dynamic OG images: drop the URL into or an tag and Rendex serves a cached copy on every share. Takes the same options as rendex_screenshot, plus an optional expiresIn. Returns { url, expiresAt, format, cacheTtl } as JSON.
Inputs: url, html, markdown, format, +37 more.
Capture a screenshot or PDF of any webpage, raw HTML, or Markdown. Supports full-page capture, dark mode, ad blocking, custom viewports, CSS/JS injection, cookie/header injection, PDF output, HTML and Markdown rendering, and progressive fallback for heavy sites. Returns partial renders on timeout by default (bestAttempt mode).
Inputs: url, html, markdown, format, +36 more.
Create a Rendex Watch — monitor a URL on a schedule and get notified when it changes (real-Chrome visual diff with a highlighted overlay, an extracted-text diff, or both). An active watch captures its baseline immediately. Returns the created watch as JSON.
Inputs: url (required), name, intervalMinutes, diffMode, +6 more.
Delete a watch and its run history. Irreversible.
Inputs: id (required).
Fetch one watch by ID, including its current baseline image URL and status. Returns JSON.
Inputs: id (required).
List your watches (newest first), optionally filtered by status and paged. Returns { items, nextCursor }.
Inputs: status, cursor, limit.
Run an immediate check now (charges 1 credit). Returns the queued run; poll watch_runs for the result or receive a watch.changed webhook.
Inputs: id (required).
Read a watch's run history (newest first), paged. Each run includes changed, diffScore, and signed before/after/overlay image URLs. Returns { items, nextCursor }.
Inputs: id (required), cursor, limit.
Dry-run a watch config BEFORE creating it — render the proposed config once and report what was captured + whether the page is reachable (and the text a text-watch would compare). Creates no watch, no baseline, no diff. Use this to validate a selector/scope/identity first. Returns JSON.
Inputs: url (required), name, intervalMinutes, diffMode, +6 more.
Update a watch in place — pause/resume (paused), re-point (url), change schedule/diff/notify settings, or turn a channel off (webhookUrl/notifyEmail = null). Only the fields you send change; renderParams is deep-merged over the existing config. A scope change (url/selector/fullPage/size/device) re-baselines on the next check. Returns the updated watch as JSON.
Inputs: id (required), url, name, intervalMinutes, +7 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 11 tools
The two tool families are clearly separated (rendering vs. watch management), and each watch operation has a distinct role. However, rendex_screenshot and rendex_render_link share nearly the same rendering pipeline and options, and watch_run vs. watch_runs differ by only one letter, so a couple of tools could still be misselected without careful reading.
All tool names use snake_case and a recognizable family prefix: rendex_* for rendering and watch_* for watch management. The imperative verb pattern is mostly consistent within the watch family, though watch_runs is a noun rather than a verb and rendex_screenshot reads as a noun, creating minor inconsistency.
At 11 tools, the surface is well-scoped and reasonable for the server's dual purpose: three rendering/capture tools and eight watch lifecycle tools. Each tool has a clear job, and none feel redundant or unnecessary.
The watch family is fully fleshed out with create, read, list, update, delete, test, run, and history operations. The rendering family covers capture, extraction, and hosted-link generation, which covers the apparent domain without obvious dead ends.
Screenshot, PDF and Open Graph image API for AI agents: capture pages, render PDFs, make OG images.
Screenshot API for AI agents. Any public page as image or PDF, banners hidden, 227 countries.
Generate images, GIFs, videos, and PDFs from HTML, URLs, or templates — from your AI agent.
Generate images and PDFs from HTML/CSS, live websites, and reusable templates.
