How do I get an API key?
Sign up for free at snap-render.com — you get 200 screenshots per month with no credit card required.
SnapRender MCP Server
@User0856
Basic information
About SnapRender MCP Server
Official integrations for SnapRender Screenshot API — MCP server, SDKs, OpenClaw, ChatGPT Actions, Postman
SnapRender MCP Server config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"snaprender": {
"command": "npx",
"args": [
"-y",
"snaprender-mcp"
],
"env": {
"SNAPRENDER_API_KEY": "sk_live_your_key_here"
}
}
}
}SnapRender MCP Server tools
11Capture a screenshot of a website URL, raw HTML, or Markdown content. Provide exactly one of: url, html, or markdown. Returns the image as a PNG, JPEG, WebP, or PDF. Supports device emulation (iPhone, Pixel, iPad), dark mode, ad blocking, cookie banner removal, full-page capture, and custom viewports.
Check if a screenshot is already cached without capturing a new one. Does not count against your quota. Pass the same parameters you would use for take_screenshot so the cache key matches correctly.
Generate a signed URL for a screenshot that can be used without an API key. Useful for embedding screenshots in emails, documents, or sharing with third parties. Signing is free, rendering the URL consumes one credit. URLs expire after the specified duration.
Extract content from a web page. Returns structured data based on the extraction type. Supports: markdown (readable content), text (plain text), html (raw HTML), article (structured with title/author/excerpt), links (all page links), metadata (OG tags, title, description).
Create a batch screenshot job for multiple URLs (1-50). Returns immediately with a job ID. Use get_batch_status to poll for results (wait 2-5 seconds between polls). All URLs share the same screenshot options. Each URL consumes one credit; failed URLs get credits rolled back.
Get the status of a batch screenshot job. Poll this until status is 'completed' or 'failed' (wait 2-5 seconds between polls). Completed items include presigned download URLs valid for 24 hours.
List all webhook subscriptions on your account. Returns webhook IDs, URLs, subscribed events, and creation dates.
Create a webhook subscription for event notifications. Events: screenshot.completed (batch job done), quota.warning (80% used), quota.exceeded (100% used). Max 5 webhooks per account. Payloads are signed with HMAC-SHA256. Save the returned secret to verify signatures.
Delete a webhook subscription by ID. This cannot be undone.
Send a test payload to a webhook endpoint to verify it receives events correctly. Returns the delivery status and HTTP response code.
Get current month's screenshot usage statistics including screenshots used, limit, and remaining quota.
Overview
What is SnapRender?
SnapRender is an MCP (Model Context Protocol) server that integrates the SnapRender Screenshot API, enabling AI agents to capture website screenshots as PNG, JPEG, WebP, or PDF. It is designed for developers building MCP-compatible clients like Claude Desktop, Smithery, or custom workflows.
How to use SnapRender?
Connect from any MCP client using the hosted URL https://app.snap-render.com/mcp with an API key in the Authorization or X-API-Key header. Alternatively, run locally via npx snaprender-mcp with stdio transport. Tools include take_screenshot, check_screenshot_cache, and get_usage.
Key features of SnapRender
- Capture screenshots as PNG, JPEG, WebP, or PDF
- Control viewport size (320–3840 pixels wide)
- Full-page capture for scrollable content
- Device presets (iPhone 14, iPad Pro, etc.)
- Ad blocking and cookie banner removal (default on)
- Check screenshot cache without consuming quota
- Get monthly usage statistics
Use cases of SnapRender
- Generate visual previews for link unfurling in chatbots
- Automate cross‑device website testing and comparison
- Capture full‑page reports or documentation screenshots
- Monitor website changes with regular snapshots
- Integrate screenshot capabilities into AI agent workflows
Frequently asked questions
What’s the difference between remote and local usage?
The remote server requires no installation and uses Streamable HTTP; the local server uses stdio and needs Node.js and `npx`. Remote works with any MCP client; local is suited for Claude Desktop or Claude Code.
Which output formats are supported?
PNG, JPEG, WebP, and PDF. Quality and format can be specified per request.
What authentication is required?
Authenticate via the `X-API-Key` header or `Authorization: Bearer` header with your API key.
Is there a screenshot quota?
Yes, the free plan includes 200 screenshots per month. You can check usage with the `get_usage` tool.
More Other MCP servers
Codelf
unbugA search tool helps dev to solve the naming things problem.
14.2K
YOUB
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Hindsight
vectorize-ioHindsight: Agent Memory That Learns
50.4K
Health by Dr Brad
Dr Brad StanfieldHealth by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one
Sequential Thinking
modelcontextprotocolModel Context Protocol Servers
88.2K
Comments