screenshotfreeapi
Click 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., "@screenshotfreeapi 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.
screenshotfreeapi-mcp
MCP server for ScreenshotFreeAPI — capture websites, render HTML/PDF, and fetch app store listing screenshots from any MCP-compatible AI client (Claude Desktop, Cursor, VS Code Copilot, Cline, Windsurf, etc.).
Setup
Get an API key from your ScreenshotFreeAPI dashboard, then add this server to your MCP client's config.
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"screenshotfreeapi": {
"command": "npx",
"args": ["-y", "screenshotfreeapi-mcp"],
"env": {
"SCREENSHOTFREEAPI_KEY": "sfa_your_api_key_here"
}
}
}
}Other MCP clients (Cursor, Cline, Windsurf) use the same command/args/env shape in their own config file — consult your client's docs for the config file location.
Related MCP server: PuppeteerMCP Server
Environment variables
Variable | Required | Description |
| Yes | Your API key ( |
| No | Override the API base URL. Defaults to |
Tools
Tool | Description |
| Capture a website screenshot (PNG/JPEG/WebP/PDF), with AI element targeting, full-page, custom viewport, and ad-block options. |
| Capture app store listing screenshots (iOS/Android) by app name or bundle ID. |
| Render raw HTML/CSS to an image or PDF. |
| Poll the status of a screenshot job. |
| Fetch the result (URLs + metadata) of a completed job. |
| List recent jobs for the authenticated account. |
| Check remaining screenshot quota and current plan. |
All capture tools are asynchronous: they enqueue a job and return a jobId. Use get_job_status to poll, then get_job_result once status is completed.
Local development
npm install
npm run dev # run directly with tsx
npm run build # compile to dist/ for npx/publish
npm run typecheckLicense
MIT
Available Tools
7 toolscheck_quotaA
Check the remaining screenshot quota and current plan for the authenticated API key.
Inputs: no named parameters.
get_job_resultA
Retrieve the screenshot URLs and metadata for a completed job. Returns presigned URLs (15-minute TTL). Returns an error if the job is still in progress.
Inputs: jobId (required).
get_job_statusA
Poll the current status and progress of a screenshot job. Status values: queued → processing → completed | failed.
Inputs: jobId (required).
list_jobsA
List recent screenshot jobs for the authenticated API key. Filter by status or type.
Inputs: status, type, limit.
render_htmlA
Render a raw HTML string (email template, certificate, report card, etc.) to a screenshot image. Requires STARTER plan.
Inputs: html (required), css, format, dimensions, +1 more.
screenshot_mobileA
Fetch app store listing screenshots for any iOS or Android app by name or bundle/package ID. Returns screenshots from Google Play and/or the Apple App Store along with rich metadata (version, rating, reviews, category).
Inputs: appName, bundleId, platform, waitForResult.
screenshot_webA
Capture a screenshot of any public website URL. Supports AI-targeted sections, full-page capture, PDF export, and custom viewport dimensions. Returns a presigned URL to the screenshot image.
Inputs: url (required), description, element, format, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool targets a distinct aspect of the screenshot service: quota checking, job management (listing, status, results), and three distinct screenshot sources (web, mobile, HTML). No two tools have overlapping functionality.
Tool names generally follow a verb_noun pattern (check_quota, get_job_result, get_job_status, list_jobs, render_html), but screenshot_mobile and screenshot_web use a noun-verb style. This minor inconsistency reduces the score slightly.
With 7 tools, the server is well-scoped for its purpose: it covers screenshot generation from multiple sources, job tracking, and quota checking without unnecessary clutter.
The tool surface covers the core screenshot workflow (create, track, retrieve) and multiple input types. Minor gaps include no way to cancel/delete jobs or manage API keys, but these are not critical for basic usage.
Maintenance
Related MCP Connectors
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
SnapRender gives AI agents eyes on the web through a hosted MCP server. Send a public URL and get the page back as an image, a PDF or clean markdown, with no browser to run or maintain. Capture the viewport or the full page as PNG, JPEG, WebP or PDF, at desktop size or with a phone, tablet or laptop preset, in light or dark mode. Ads and cookie banners are removed by default, and you can hide elements or click one before the capture. extract_content reads the same page as markdown, text, article, links or metadata, so an agent can see a page and read it in one session. Made for monitoring and client work: batch up to 50 URLs in one job, check the cache for free before spending a capture, share signed links that render without an API key, and get webhooks when a batch finishes or a scheduled capture spots a change. Track competitors' pricing and landing pages, or send clients current screenshots of their sites. Connect with OAuth (Google, GitHub or email) or an API key. Works with Claude, ChatGPT, Cursor, VS Code and any MCP client. Free plan: 200 screenshots a month, no credit card. Paid plans from $9 a month for 2,000 up to $199 a month for 200,000. Home: https://snap-render.com Docs: https://snap-render.com/ai-agents
Screenshots, PDFs, image editing, QR codes, email validation and more through one hosted MCP server.
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Related MCP Servers
- AlicenseBqualityCmaintenanceAn official MCP server implementation that allows AI assistants to capture website screenshots through the ScreenshotOne API, enabling visual context from web pages during conversations.1194 npm38MIT
- AlicenseBqualityDmaintenanceAn MCP server that enables AI assistants to capture and analyze web page screenshots using Puppeteer, supporting multi-breakpoint captures, error reporting, and page interactions.165 npm6MIT
- AlicenseBqualityCmaintenanceAn MCP server that enables capturing website screenshots with full-page, element-specific, and device-responsive capabilities through natural language commands.321 npm62MIT
- FlicenseNot gradedqualityDmaintenanceScreenshot & Render API for AI Agents. MCP Server lets Claude, Cursor capture webpages and render HTML. Direct access, no VPN needed.-