@rendershot/mcp-server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@rendershot/mcp-server Take a screenshot of https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@rendershot/mcp-server
Model Context Protocol (MCP) server for the Rendershot screenshot and PDF generation API. Lets AI agents (Claude, Cursor, etc.) capture screenshots and generate PDFs directly as tool calls.
Source: github.com/Rendershot/rendershot-mcp-server
Quick start
No installation needed — run with npx:
RENDERSHOT_API_KEY=your_key npx @rendershot/mcp-serverRelated MCP server: RendShot MCP Server
Claude Desktop setup
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"rendershot": {
"command": "npx",
"args": ["-y", "@rendershot/mcp-server"],
"env": {
"RENDERSHOT_API_KEY": "your_api_key_here"
}
}
}
}Cursor / VS Code setup
Add to your MCP settings:
{
"rendershot": {
"command": "npx",
"args": ["-y", "@rendershot/mcp-server"],
"env": {
"RENDERSHOT_API_KEY": "your_api_key_here"
}
}
}Environment variables
Variable | Required | Default | Description |
| Yes | — | Your Rendershot API key |
| No |
| API base URL (override for self-hosting) |
Tools
take_screenshot
Capture a screenshot of a URL or HTML string. Returns a base64-encoded image.
Parameter | Type | Default | Description |
| string | — | Page URL to screenshot (one of url/html required) |
| string | — | Raw HTML to render (one of url/html required) |
|
|
| Output image format |
| 1–100 |
| JPEG quality (ignored for PNG) |
| 1–3840 |
| Viewport width in pixels |
| 1–2160 |
| Viewport height in pixels |
| boolean |
| Capture the full scrollable page |
| string |
|
|
| 0–10000 |
| Extra delay after page load (ms) |
|
| — | Remove cookie banners/popups before capture. |
|
| — | Custom HTTP headers sent with the render request. Max 30, values ≤ 2 KB. |
| array | — | Session cookies to inject. Each needs |
|
| — | HTTP Basic auth. Sent on 401 challenge |
generate_pdf
Generate a PDF from a URL or HTML string. Returns the PDF as a base64-encoded string.
Parameter | Type | Default | Description |
| string | — | Page URL (one of url/html required) |
| string | — | Raw HTML (one of url/html required) |
|
|
| Paper size |
|
|
| Page orientation |
| boolean |
| Print background graphics/colors |
| string |
| Same as screenshot |
| 0–10000 |
| Extra delay after page load (ms) |
|
| — | Same as screenshot |
|
| — | Same as screenshot |
| array | — | Same as screenshot |
|
| — | Same as screenshot |
bulk_render
Submit up to 20 screenshot or PDF jobs in one call. All jobs run in parallel and results include base64 output per job.
Parameter | Type | Description |
| array (1–20) | Array of job objects, each with |
Returns a JSON object with credits_used, credits_remaining, and a results array containing index, result (base64), and any error per job.
check_balance
Check remaining API credits and plan details. No parameters.
Notes
All render calls use async mode internally and poll until the job completes (up to 5 minutes).
Screenshots return MCP
imagecontent — agents can display them inline.PDFs return base64-encoded text; agents can save them to disk or pass them on.
Errors from the API (rate limits, credit exhaustion, invalid URLs) surface as MCP errors with the original error code.
Requirements
Node.js 18+
License
MIT
Available Tools
4 toolsbulk_renderA
Submit up to 20 screenshot or PDF render jobs in a single request. Returns results for all jobs including base64-encoded output.
Inputs: jobs (required), output_dir.
check_balanceA
Check the remaining API credits and current plan details for the configured API key.
Inputs: no named parameters.
generate_pdfC
Generate a PDF from a web page or HTML content. Returns the PDF as a base64-encoded string.
Inputs: url, html, format, orientation, +8 more.
take_screenshotB
Capture a screenshot of a web page or HTML content. Returns a base64-encoded PNG or JPEG image.
Inputs: url, html, format, quality, +10 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clear, distinct purpose: bulk_render for batch jobs, check_balance for credits, generate_pdf and take_screenshot for single outputs. No overlap.
All tools use consistent snake_case with verb_noun pattern (bulk_render, check_balance, generate_pdf, take_screenshot).
4 tools is well-scoped for a focused rendering server, covering single and batch operations plus balance checking without unnecessary extras.
Covers core rendering tasks (screenshot, PDF, batch) and account monitoring. Minor gap: no way to manage or cancel batch jobs, but results are returned immediately.
Maintenance
Related MCP Connectors
Generate images, GIFs, videos, and PDFs from HTML, URLs, or templates — from your AI agent.
Screenshot, PDF and Open Graph image API for AI agents: capture pages, render PDFs, make OG images.
Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API
Give your agent eyes: screenshots of any web page it can see, pages as markdown, and PDFs.
Related MCP Servers
- AlicenseAqualityBmaintenanceCapture screenshots, generate PDFs, and render HTML to images via AI agents. Supports batch capture, geo-targeting, async webhooks, and CSS/JS injection.1169 npm6MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to generate images from HTML/CSS, capture URL screenshots, and manage reusable templates through the RendShot API. Provides tools for rendering visual content programmatically within AI workflows.-
- AlicenseAqualityDmaintenanceEnables AI agents to capture screenshots and generate PDFs from URLs or HTML via the SnapForge API.332 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to capture any public URL as PNG, JPEG, or PDF via REST API or MCP tools, including screenshot capture, page description, and PDF rendering.12 npmMIT