snapforge-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., "@snapforge-mcp Screenshot 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.
snapforge-mcp
MCP server for SnapForge — give your AI agents three tools to read and render the web:
snapforge_screenshot— capture any URL or HTML as PNG/JPEG (full-page by default)snapforge_pdf— render a URL or HTML to PDF (singlePageoption + clean pagination, no cut blocks)snapforge_markdown— extract clean Markdown from any page (article extraction) → perfect for feeding live web content to an LLM
Works with Claude Code & Desktop, Cursor, Kilo Code, Cline, Windsurf, Zed, VS Code, Hermes, OpenClaw — and any MCP client.
Examples
Real outputs, generated live from the API:

More samples: full-page screenshot (any height) · pricing page · mobile viewport · PDFs (invoice, single-page article, multi-page report, certificate) · a page as Markdown
Related MCP server: RendShot MCP Server
Setup
Get a free API key at https://snapforge.org (100 one-time renders, no card), then:
Hosted (zero install) — recommended
Point any MCP client at the remote server, with your key in the x-api-key header:
https://snapforge.org/mcpLocal (stdio) — Claude Desktop / Claude Code / any client
{
"mcpServers": {
"snapforge": {
"command": "npx",
"args": ["-y", "snapforge-mcp"],
"env": { "SNAPFORGE_API_KEY": "sf_your_key" }
}
}
}Claude Code plugin (one-click)
/plugin marketplace add sporty303/snapforge-mcp
/plugin install snapforge@snapforgeEnvironment
SNAPFORGE_API_KEY(required)SNAPFORGE_BASE_URL(optional, defaults tohttps://snapforge.org)
License
MIT
Available Tools
3 toolssnapforge_markdownSnapForge URL to MarkdownARead-onlyInspect
Extract a clean Markdown version of a public URL or raw HTML (article extraction + HTML→Markdown). Great for feeding live web content to an LLM.
Inputs: url, html, delay, waitUntil. Returns: markdown, savedPath
snapforge_pdfSnapForge PDFBRead-onlyInspect
Render a public URL or raw HTML to a PDF. The PDF is written to a temp file and its path is returned.
Inputs: url, html, delay, margin, +5 more. Returns: bytes, savedPath
snapforge_screenshotSnapForge screenshotARead-onlyInspect
Capture a screenshot of a public URL or raw HTML and return it as an image (PNG/JPEG). Full-page by default.
Inputs: url, html, delay, scale, +6 more. Returns: bytes, mimeType, savedPath
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct output format (image, PDF, markdown) with no overlap in functionality, making selection unambiguous.
All tools follow the consistent prefix 'snapforge_' followed by a clear noun describing the output, forming a predictable pattern.
Three tools is an appropriate scope for a server focused on converting web content to common formats—neither too few nor too many.
Covers the three most common output conversions (image, PDF, markdown), though additional options like plain text or specific rendering parameters are absent.
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.
Give your agent eyes: screenshots of any web page it can see, pages as markdown, and PDFs.
Screenshot API for AI agents. Any public page as image or PDF, banners hidden, 227 countries.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to capture webpage screenshots, generate PDFs from URLs or HTML, and extract rich metadata like Open Graph and JSON-LD data. It provides tools for web-to-image/PDF conversion and structured data extraction through the Junipr API.1MIT
- 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.-

@rendershot/mcp-serverofficial
AlicenseAqualityDmaintenanceEnables AI agents to capture screenshots and generate PDFs from URLs or HTML via the Rendershot API.43MIT- AlicenseNot gradedqualityCmaintenanceEnables 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