The SnapRender MCP server provides three core capabilities:
Take Screenshots (take_screenshot): Capture any website (http/https) as PNG, JPEG, WebP, or PDF with extensive options:
Custom viewport dimensions (width: 320–3840px, height: 200–10000px)
Device emulation: iPhone 14, iPhone 15 Pro, Pixel 7, iPad Pro, MacBook Pro
Dark mode CSS emulation
Full-page (scrollable) capture
Ad/tracker blocking and cookie banner removal (both enabled by default)
Delay after page load (0–10000ms)
Hide or click specific elements via CSS selectors before capture
JPEG/WebP quality control (1–100)
Check Screenshot Cache (check_screenshot_cache): Verify if a screenshot for a given URL and format is already cached — without consuming any quota.
Get Usage Statistics (get_usage): Retrieve your current (or specified) month's screenshot usage, including screenshots used, limit, and remaining quota.
Official integrations for SnapRender Screenshot API — capture screenshots of any website as PNG, JPEG, WebP, or PDF.
SnapRender runs a hosted MCP server — connect from any MCP client with zero install:
https://app.snap-render.com/mcpTransport: Streamable HTTP (MCP spec 2025-03-26)
Auth: X-API-Key header or Authorization: Bearer header
Tools: take_screenshot, check_screenshot_cache, get_usage
Prompts: screenshot_website, compare_devices
{
"mcpServers": {
"snaprender": {
"type": "streamable-http",
"url": "https://app.snap-render.com/mcp",
"headers": {
"Authorization": "Bearer sk_live_your_key_here"
}
}
}
}# Initialize a session
curl -X POST https://app.snap-render.com/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "X-API-Key: sk_live_your_key_here" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'The server returns an Mcp-Session-Id header — include it in subsequent requests to reuse the session.
Install via Smithery for automatic setup with any MCP client.
Related MCP server: Screenshot API
If you prefer running locally via stdio transport:
{
"mcpServers": {
"snaprender": {
"command": "npx",
"args": ["-y", "snaprender-mcp"],
"env": {
"SNAPRENDER_API_KEY": "sk_live_your_key_here"
}
}
}
}See mcp-server/ for full documentation.
Remote (hosted) | Local ( | |
Install | None — just an HTTPS URL | Requires Node.js + npx |
Transport | Streamable HTTP | stdio |
Use case | Any MCP client, Smithery, web apps | Claude Desktop, Claude Code |
take_screenshotCapture a screenshot of any website. Returns the image as PNG, JPEG, WebP, or PDF.
Parameter | Type | Required | Description |
| string | Yes | URL to capture (http:// or https://) |
| string | No |
|
| integer | No | Viewport width 320-3840 (default: 1280) |
| integer | No | Viewport height 200-10000 (default: 800) |
| boolean | No | Capture entire scrollable page |
| string | No |
|
| boolean | No | Enable dark mode |
| boolean | No | Block ads (default: true) |
| boolean | No | Remove cookie banners (default: true) |
| integer | No | JPEG/WebP quality 1-100 (default: 90) |
| integer | No | Wait ms after page load (default: 0) |
| string | No | Comma-separated CSS selectors to hide |
| string | No | CSS selector to click before capture |
check_screenshot_cacheCheck if a screenshot is cached without capturing. Does not count against quota.
Parameter | Type | Required | Description |
| string | Yes | URL to check |
| string | No | Output format (default: |
get_usageGet screenshot usage statistics.
Parameter | Type | Required | Description |
| string | No | Month in |
Framework | Directory | Description |
|
| |
|
| |
|
| |
|
| |
Separate repo | Community node for n8n workflows (npm) |
Integration | Description | Setup Time |
Skill file for OpenClaw AI agent | 5 min | |
OpenAPI spec for Custom GPTs and OpenAI function calling | 5 min | |
Pre-built API requests for Postman | 1 min |
# Node.js
npm install snaprender
# Python
pip install snaprendercurl "https://app.snap-render.com/v1/screenshot?url=https://example.com" \
-H "X-API-Key: sk_live_your_key_here" \
-o screenshot.pngSign up free at snap-render.com — 200 screenshots/month, no credit card required.
Remote MCP Server — Streamable HTTP endpoint
MCP Server on npm (npx snaprender-mcp)
Node.js SDK (npm install snaprender)
Python SDK (pip install snaprender)
LangChain Python Tool (pip install langchain-snaprender)
LangChain.js Tool (npm install langchain-snaprender)
CrewAI Tool (pip install crewai-snaprender)
AutoGen Tool (pip install autogen-ext-snaprender)
n8n Community Node (npm install n8n-nodes-snaprender)
MIT
Check if a screenshot is already cached without capturing a new one. Does not count against your quota.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to check | |
| format | No | Output format (default: png) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description discloses a key behavioral trait: it does not count against quota. This is important for usage optimization. It does not mention return values or side effects, but the tool is simple and low-risk.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero wasted words. The description is front-loaded with the primary purpose and immediately adds a key differentiator (quota). Perfect conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple cache-check tool with no output schema and clear sibling context, the description is sufficient. It explains the core function and a critical behavioral note. Minor gap: does not describe the return format (e.g., boolean), but not essential for an agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has 100% description coverage with basic descriptions for 'url' and 'format'. The description adds no additional insight beyond the schema, so it meets the baseline for schema-rich tools but does not enhance understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'check' and the resource 'screenshot cache'. It distinguishes from sibling 'take_screenshot' by noting it does not capture a new screenshot, and adds a unique benefit: not counting against quota. This is specific and helpful.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for verifying cache before capturing, but does not explicitly state when to use vs. 'take_screenshot' or 'get_usage'. However, the sibling context and the phrase 'without capturing a new one' provide clear contextual guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get current month's screenshot usage statistics including screenshots used, limit, and remaining quota.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description indicates a read-only operation retrieving usage statistics. Discloses what data is returned but does not mention any side effects, authentication requirements, or rate limits. Adequate for a simple getter.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 13 words, directly communicates purpose and included fields. No wasted words; perfectly concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and no output schema, description adequately lists the three pieces of information returned (screenshots used, limit, remaining quota). Could specify data types or format, but minimally complete for a simple statistics endpoint.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Input schema has zero parameters, so schema_description_coverage is 100%. Baseline for zero-parameter tools is 4; description adds no parameter info as none are needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it retrieves current month's screenshot usage statistics with specific fields (screenshots used, limit, remaining quota). Differentiates from sibling tools (check_screenshot_cache, take_screenshot) which focus on capturing or caching screenshots.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus siblings. Usage is implied by the name and description, but lacks when-not-to-use or alternative recommendations. For a simple stats tool, this is minimally adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Capture a screenshot of any website. 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.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to capture (must start with http:// or https://) | |
| format | No | Output format (default: png) | |
| width | No | Viewport width in pixels (default: 1280) | |
| height | No | Viewport height in pixels (default: 800) | |
| full_page | No | Capture entire scrollable page (default: false) | |
| quality | No | Image quality for JPEG/WebP, 1-100 (default: 90) | |
| delay | No | Milliseconds to wait after page load (default: 0) | |
| dark_mode | No | Enable dark mode CSS emulation (default: false) | |
| block_ads | No | Block advertisements and trackers (default: true) | |
| block_cookie_banners | No | Remove cookie consent banners (default: true) | |
| device | No | Device preset for mobile/tablet emulation | |
| hide_selectors | No | Comma-separated CSS selectors to hide before capture | |
| click_selector | No | CSS selector to click before capture |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It mentions output formats and features but lacks details on error behavior, rate limits, or prerequisites.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence covering core action and key features. No fluff, front-loaded with main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
13 parameters, no output schema, no annotations. Description lists formats but does not specify how the result is returned (e.g., binary, URL). Could be more complete on output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. Description adds overview of features but does not elaborate on parameter usage beyond what schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states 'Capture a screenshot of any website' with specific verb and resource. It lists many features like format support, device emulation, dark mode, etc., clearly distinguishing it from sibling tools (check_screenshot_cache, get_usage).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this vs alternatives. The sibling tools are about cache checking and usage, so the context is implied but not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0check_screenshot_cacheget_usagetake_screenshotEach tool has a distinct purpose: checking cache, retrieving usage stats, and capturing screenshots. There is no overlap in functionality.
All tools follow a consistent verb_noun pattern with snake_case, making the set predictable and easy to understand.
Three tools is an appropriate size for a focused screenshot service, covering essential operations without unnecessary complexity.
The tool set covers the core workflow of capturing screenshots, with supplementary tools for cache checking and usage tracking. A minor gap is the absence of cache management operations.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Hosted browser for AI agents: screenshots, post-JS DOM, console, WCAG. No install, no API key.
Screenshots, PDFs and Markdown from any URL or HTML for AI agents, via the SnapForge API
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/User0856/snaprender-integrations'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
