@Rendershot/ Server
БесплатноНе проверенEnables AI agents to capture screenshots and generate PDFs from URLs or HTML via the Rendershot API.
Описание
Enables AI agents to capture screenshots and generate PDFs from URLs or HTML via the Rendershot API.
README
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-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 |
|---|---|---|---|
RENDERSHOT_API_KEY |
Yes | — | Your Rendershot API key |
RENDERSHOT_BASE_URL |
No | https://api.rendershot.io |
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 |
|---|---|---|---|
url |
string | — | Page URL to screenshot (one of url/html required) |
html |
string | — | Raw HTML to render (one of url/html required) |
format |
png | jpeg |
png |
Output image format |
quality |
1–100 | 85 |
JPEG quality (ignored for PNG) |
viewport_width |
1–3840 | 1280 |
Viewport width in pixels |
viewport_height |
1–2160 | 720 |
Viewport height in pixels |
full_page |
boolean | false |
Capture the full scrollable page |
wait_for |
string | dom_content_loaded |
load | dom_content_loaded | network_idle | commit | CSS selector |
delay_ms |
0–10000 | 0 |
Extra delay after page load (ms) |
ai_cleanup |
fast | thorough |
— | Remove cookie banners/popups before capture. fast uses JS heuristics (1 credit); thorough adds an LLM pass (3 credits) |
headers |
{ [name]: value } |
— | Custom HTTP headers sent with the render request. Max 30, values ≤ 2 KB. Host / Cookie / Content-Length / Sec-* / Connection rejected |
cookies |
array | — | Session cookies to inject. Each needs name, value, and one of domain / url. Optional: path, expires, http_only, secure, same_site (Lax | Strict | None). Max 50 |
basic_auth |
{ username, password } |
— | 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 |
|---|---|---|---|
url |
string | — | Page URL (one of url/html required) |
html |
string | — | Raw HTML (one of url/html required) |
format |
A3 | A4 | Letter | Legal |
A4 |
Paper size |
orientation |
portrait | landscape |
portrait |
Page orientation |
print_background |
boolean | true |
Print background graphics/colors |
wait_for |
string | dom_content_loaded |
Same as screenshot |
delay_ms |
0–10000 | 0 |
Extra delay after page load (ms) |
ai_cleanup |
fast | thorough |
— | Same as screenshot |
headers |
{ [name]: value } |
— | Same as screenshot |
cookies |
array | — | Same as screenshot |
basic_auth |
{ username, password } |
— | 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 |
|---|---|---|
jobs |
array (1–20) | Array of job objects, each with type: "screenshot" or type: "pdf" plus the same fields as the individual tools |
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
Установка @Rendershot/ Server
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/Rendershot/rendershot-mcp-serverFAQ
@Rendershot/ Server MCP бесплатный?
Да, @Rendershot/ Server MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для @Rendershot/ Server?
Нет, @Rendershot/ Server работает без API-ключей и переменных окружения.
@Rendershot/ Server — hosted или self-hosted?
Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.
Как установить @Rendershot/ Server в Claude Desktop, Claude Code или Cursor?
Открой @Rendershot/ Server на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare @Rendershot/ Server with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
