A
licenseNot graded
qualityD
maintenanceEnables 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.
18 npm
MIT
screenshotapi-mcp
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., "@screenshotapi-mcp 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.
ScreenshotAPI MCP Server
An MCP (Model Context Protocol) server for ScreenshotAPI — capture screenshots, extract page content as Markdown, and manage your account from any MCP-compatible AI agent.
Tools
Tool | Description |
| Capture a screenshot of any URL with full control over viewport, device emulation, format, and blocking options |
| Capture a specific CSS selector on a page — great for headers, articles, or widgets |
| Render a page and return its content as clean Markdown |
| Check your account quota, credits balance, and feature entitlements |
| Retrieve a screenshot job by ID (for polling async jobs) |
Related MCP server: bigapi
Quick Start
Run directly with npx — no installation needed:
SCREENSHOTAPI_KEY=your_api_key npx --yes screenshotapi-mcpClaude Desktop Configuration
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"screenshotapi": {
"command": "npx",
"args": ["--yes", "screenshotapi-mcp"],
"env": {
"SCREENSHOTAPI_KEY": "sk_live_your_api_key_here"
}
}
}
}Other MCP Clients
Any MCP client can connect via stdio. Run the server directly:
SCREENSHOTAPI_KEY=your_api_key node build/index.jsEnvironment Variables
Variable | Required | Description |
| Yes | Your ScreenshotAPI API key ( |
| No | API base URL (default: |
Get your API key at screenshotapi.tech/dashboard.
Building from Source
git clone https://github.com/your-org/screenshotapi-mcp.git
cd screenshotapi-mcp
npm install
npm run build
SCREENSHOTAPI_KEY=your_key node build/index.jsLicense
MIT
Available Tools
5 toolscapture-elementA
Capture a specific element on a page by CSS selector. Useful for capturing headers, articles, widgets, or any identifiable DOM element without rendering the entire page.
Inputs: url (required), selector (required), delay, width, +8 more.
convert-to-markdownA
Render a webpage and return its content as clean Markdown. Useful for extracting readable text from any URL for analysis, summarization, or data processing.
Inputs: url (required).
get-screenshotA
Retrieve a screenshot job by its ID. Use this to poll async jobs or retrieve previously captured screenshots.
Inputs: id (required).
get-usageA
Check your ScreenshotAPI account usage — remaining screenshots, credits balance, plan details, and feature entitlements.
Inputs: no named parameters.
render-screenshotB
Capture a screenshot of any website URL. Returns the image URL, dimensions, and file size. Supports device emulation, dark mode, ad/cookie/tracker blocking, geo-targeting, and full-page captures.
Inputs: url (required), delay, width, device, +11 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A3.7/5.0
Scored across 5 tools
Disambiguation4/5
Tools are mostly distinct: render-screenshot captures full pages, capture-element targets specific DOM elements, convert-to-markdown extracts text, get-screenshot retrieves by ID, and get-usage is account-related. The only minor overlap is between the two capture tools, but their descriptions clearly differentiate full-page vs. element capture.
Naming Consistency5/5
All tool names follow a consistent verb-noun pattern with hyphenated lowercase (render-screenshot, capture-element, convert-to-markdown, get-usage, get-screenshot). The verbs clearly indicate actions, and the nouns identify the object, making the naming predictable and easy to infer.
Tool Count5/5
With 5 tools, the server is well-scoped for a screenshot utility. Each tool serves a distinct purpose without redundancy, covering the core capture, retrieval, conversion, and account management needs. This count is appropriate and not overwhelming or thin.
Completeness4/5
The tool surface covers the primary workflow: capturing screenshots (full-page and element), converting to markdown, retrieving past captures, and checking usage. Minor gaps exist, such as no tool for listing all captures or deleting them, but these are not essential for the core screenshot API functionality and can be worked around.
Maintenance
ActivityStale
ResponsivenessNo recent community issues
Related MCP Connectors
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Scraper API for HTML, Markdown, and screenshots, web search, and account usage for AI agents.
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API
Related MCP Servers
- AlicenseAqualityBmaintenanceDeterministic file operations for AI agents: 40 operations over plain HTTPS. PDF merge, split, redact, sanitize, OCR, Office and PDF to Markdown, RAG chunking, charts, QR codes, C2PA AI labelling. find_tool suggests the right one. $0.01 per operation, 100 free, no signup, credits never expire.552 npmMIT
Grabbitofficial
AlicenseNot gradedqualityCmaintenanceScreenshot MCP for agents. Send a public URL, get a pixel-perfect CDN image. Full page, header, mobile, or custom. Cookie banner suppression. Handles sites that block headless browsers. Works with Claude, Cursor, Codex. $0.002/grab.MIT- AlicenseAqualityBmaintenanceEnables MCP-compatible AI agents to search, scrape, crawl, map, and interact with live web pages, returning clean, structured, agent-ready content. It also supports recurring page monitoring, autonomous deep research, and credit-usage checks.26181,541 npm1MIT