MCP.so
Sign In

Rendex

@copperline-labs

RepositoryHomepage

About Rendex

MCP server for Rendex — capture screenshots, generate PDFs, and render HTML to images of any webpage via AI agents. Claude, Cursor, Windsurf compatible.

#screenshot#pdf#html-to-image#rendering#web-capture#claude#ai-agent#rendex

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "rendex": {
      "command": "npx",
      "args": [
        "-y",
        "@copperline/rendex-mcp"
      ],
      "env": {
        "RENDEX_API_KEY": "your-api-key"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Rendex?

Rendex is an MCP server that lets AI agents render raw HTML, Markdown, or any URL to an image or PDF using the Model Context Protocol. It integrates with the Rendex platform and is designed for agents in Claude, Cursor, Windsurf, ChatGPT, and similar clients.

How to use Rendex?

Install via npx and configure your MCP client with a RENDEX_API_KEY environment variable, or connect to the remote hosted server at https://mcp.rendex.dev/mcp using OAuth 2.1 or a static API key. The server exposes tools like rendex_screenshot, rendex_extract, rendex_render_link, render_artifact, and eight watch‑related tools.

Key features of Rendex

  • Render any URL, raw HTML, or Markdown to PNG, JPEG, WebP, or PDF.
  • Extract clean reader‑mode content as Markdown, JSON, or HTML.
  • Generate signed, hosted, edge‑cached image URLs for OG images.
  • Create branded downloadable artifacts (PDF + PNG + share page) in one call.
  • Monitor URLs with real‑Chrome visual/text diff and change alerts.

Use cases of Rendex

  • Generate dynamic OG images for blog posts or release notes.
  • Capture full‑page screenshots of webpages with custom viewport, device, or geo settings.
  • Extract readable article text from SPAs for LLM summarization or RAG ingestion.
  • Automate page‑change detection with visual diffs and webhook notifications.
  • Produce branded PDF invoices, reports, or dashboards from Markdown or HTML.

FAQ from Rendex

Do I need an API key?

Yes, you can provide one via the RENDEX_API_KEY environment variable or pass it as a Bearer token to the remote server. OAuth‑capable clients can authenticate with a one‑time email code instead.

What output formats are supported?

Screenshots can be PNG, JPEG, WebP, or PDF. Content extraction returns Markdown, JSON, or HTML. Artifacts produce PDF and/or PNG with hosted share links. The rendex_render_link tool returns a signed URL for an image.

Is there a remote hosted version of Rendex?

Yes, the server is available at https://mcp.rendex.dev/mcp with OAuth 2.1 support, so no local install is needed.

Are there any limits I should know about?

Viewport width is limited to 320–3840px, height 240–2160px. Custom CSS and JavaScript are capped at 50 KB each, and artifact content at roughly 4 MB. Geo‑targeting parameters require a Pro or Enterprise plan.

Can I run captures asynchronously?

Yes, set the async parameter to true and optionally provide a webhookUrl to receive a callback when the capture completes.

Frequently asked questions

Do I need an API key?

Yes, you can provide one via the `RENDEX_API_KEY` environment variable or pass it as a `Bearer` token to the remote server. OAuth‑capable clients can authenticate with a one‑time email code instead.

What output formats are supported?

Screenshots can be PNG, JPEG, WebP, or PDF. Content extraction returns Markdown, JSON, or HTML. Artifacts produce PDF and/or PNG with hosted share links. The `rendex_render_link` tool returns a signed URL for an image.

Is there a remote hosted version of Rendex?

Yes, the server is available at `https://mcp.rendex.dev/mcp` with OAuth 2.1 support, so no local install is needed.

Are there any limits I should know about?

Viewport width is limited to 320–3840px, height 240–2160px. Custom CSS and JavaScript are capped at 50 KB each, and artifact content at roughly 4 MB. Geo‑targeting parameters require a Pro or Enterprise plan.

Can I run captures asynchronously?

Yes, set the `async` parameter to `true` and optionally provide a `webhookUrl` to receive a callback when the capture completes.

Comments

Basic information

Category

Other

License

MIT

Transports

stdio

Author

copperline-labs

Submitted by

Dan425953

More Other MCP servers

MCP Go 🚀

mark3labs

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

8.9K

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K

AutoBrowser MCP

autobrowser-ai

Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser

6.8K

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K

Nginx UI

0xJacky

Yet another WebUI for Nginx

11.3K