mcpField
S
Screenshot

Screenshot

Local
screenshotrender.comBrowser Automation0Updated 21w ago
RepositoryVisit website

About Screenshot

ScreenshotRender is an MCP server that uses an API to capture public web pages for AI assistants, returning an inline image, hosted URL, and page metadata. It is for users who want screenshots within an MCP client conversation.

Key features

  1. 01Capture any public URL
  2. 02Capture full pages or viewports
  3. 03Set wait time and timeout
  4. 04Return hosted URL and page metadata

Use cases

  1. 01View website screenshots in a conversation
  2. 02Inspect pages with animations or lazy-loaded content

MCP support

The MCP server exposes the take_screenshot tool, which captures web pages through the ScreenshotRender API.

#screenshot#screenshot-api#website#image#rendering

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "screenshotrender": {
      "command": "npx",
      "args": [
        "-y",
        "screenshotrender-mcp"
      ],
      "env": {
        "SCREENSHOTRENDER_API_KEY": "<SCREENSHOTRENDER_API_KEY>"
      }
    }
  }
}
Run commandnpx -y screenshotrender-mcp
Environment variables to set
SCREENSHOTRENDER_API_KEYSecretYour ScreenshotRender API key (starts with sr-). Get one at https://screenshotrender.com.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmscreenshotrender-mcp1.0.1

Tools

1

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
urlstringYesThe URL of the page to screenshot. Include the scheme (https://). Example: https://stripe.com
fullPagebooleanNoCapture the entire scrollable page instead of just the 1280x720 viewport. Defaults to false.
waitintegerNoMilliseconds to wait after load before capturing, for pages with animations or lazy content. Defaults to none.
timeoutintegerNoMaximum milliseconds to wait for the page to load.

Details

From the project README

ScreenshotRender MCP server

Capture website screenshots from inside Claude, Cursor, VS Code, Windsurf, or any Model Context Protocol client. This server wraps the ScreenshotRender API so your AI assistant can render any public web page on request.

Ask your assistant: "Take a full-page screenshot of stripe.com" and the image appears right in the chat.

Tools

ToolDescription
take_screenshotCapture a screenshot of any public URL. Returns the image inline plus a hosted URL and page metadata (title, description).

Parameters

  • url (string, required) — page to capture, including https://.
  • fullPage (boolean, optional) — capture the entire scrollable page instead of the viewport.
  • wait (number, optional) — milliseconds to wait before capturing (for animations / lazy content).
  • timeout (number, optional) — max milliseconds to wait for load.

Setup

  1. Get your API key at screenshotrender.com (it starts with sr-).
  2. Add the server to your MCP client config.
Claude Desktop

Edit claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "screenshotrender": {
      "command": "npx",
      "args": ["-y", "screenshotrender-mcp"],
      "env": {
        "SCREENSHOTRENDER_API_KEY": "sr-your-key-here"
      }
    }
  }
}
Cursor / VS Code / Windsurf

Add the same block under the editor's MCP settings (mcp.json or the MCP settings UI). Restart the client and the take_screenshot tool will be available.

Environment variables

VariableRequiredDescription
SCREENSHOTRENDER_API_KEYyesYour ScreenshotRender key (sr-...).
SCREENSHOTRENDER_BASE_URLnoOverride the API base URL. Defaults to https://screenshotrender.com.

Local development

npm install
SCREENSHOTRENDER_API_KEY=sr-your-key npm run inspect   # opens MCP Inspector

The Inspector lets you call take_screenshot and view the result before shipping.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.