snaprender-mcp

take_screenshot

Read-only

Capture screenshots from a website URL, raw HTML, or Markdown as PNG, JPEG, WebP, or PDF; supports device emulation, dark mode, ad blocking, full-page capture.

Instructions

Capture 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.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No	URL to capture (must start with http:// or https://). Mutually exclusive with html and markdown.
`html`	No	Raw HTML content to render and capture (max 2MB). Mutually exclusive with url and markdown.
`cache`	No	Use cached result if available. Set to true to enable caching (default: false)
`delay`	No	Milliseconds to wait after page load (default: 0)
`width`	No	Viewport width in pixels (default: 1280)
`device`	No	Device preset for mobile/tablet emulation
`format`	No	Output format (default: png)
`height`	No	Viewport height in pixels (default: 800)
`quality`	No	Image quality for JPEG/WebP, 1-100 (default: 90)
`markdown`	No	Markdown content to render with a clean styled template and capture (max 500KB). Mutually exclusive with url and html.
`block_ads`	No	Block advertisements and trackers (default: true)
`cache_ttl`	No	Cache TTL in seconds, 0-2592000. Clamped to your plan max (default: 86400)
`dark_mode`	No	Enable dark mode CSS emulation (default: false)
`full_page`	No	Capture entire scrollable page (default: false)
`user_agent`	No	Custom user agent string to use for the request
`click_selector`	No	CSS selector to click before capture
`hide_selectors`	No	Comma-separated CSS selectors to hide before capture
`block_cookie_banners`	No	Remove cookie consent banners (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv1.5.6Oct 5, 2026

addedInput schema / properties / cache

Added value: +{
+  "description": "Use cached result if available. Set to true to enable caching (default: false)",
+  "type": "boolean"
+}

addedInput schema / properties / cache_ttl

Added value: +{
+  "description": "Cache TTL in seconds, 0-2592000. Clamped to your plan max (default: 86400)",
+  "maximum": 2592000,
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / html

Added value: +{
+  "description": "Raw HTML content to render and capture (max 2MB). Mutually exclusive with url and markdown.",
+  "type": "string"
+}

addedInput schema / properties / markdown

Added value: +{
+  "description": "Markdown content to render with a clean styled template and capture (max 500KB). Mutually exclusive with url and html.",
+  "type": "string"
+}

changedInput schema / properties / url / description

Previous value: -"URL to capture (must start with http:// or https://)"New value: +"URL to capture (must start with http:// or https://). Mutually exclusive with html and markdown."

addedInput schema / properties / user_agent

Added value: +{
+  "description": "Custom user agent string to use for the request",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "url"
-]New value: +[]

First observedv1.0.0Feb 20, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds useful behavioral context: the output media types and the rendering feature set (ad blocking, cookie banner removal, full-page capture). It omits auth/plan limits implied by cache_ttl clamping and any failure behavior for bad URLs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with what the tool does and the input constraint, then output formats, then optional features. No filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 18-parameter tool with full schema coverage and no output schema, the description adequately covers inputs and return types. It is slightly short on caching semantics (cache/cache_ttl interaction) and error handling, but nothing critical for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all 18 parameters are already documented with defaults and bounds; the baseline is 3. The description restates a subset of capabilities (device emulation, dark mode, ad blocking, full-page, viewports) without adding syntax or format detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Capture a screenshot') and enumerates the three accepted input types (url, html, markdown), which separates it cleanly from siblings like extract_content and batch_screenshots. Output formats are named as well, so an agent knows what it gets back.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Provide exactly one of: url, html, or markdown', a clear usage constraint. However it never routes to alternatives such as batch_screenshots for multiple targets or check_screenshot_cache for cached results, so sibling selection is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

take_screenshot

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools