Skip to main content
Glama
Sign In
screenshotrun-mcp

screenshotrun-mcp

Official
by screenshotrun
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

screenshotrun-mcp

npm version License: MIT

Give your AI agent the ability to see any webpage. MCP server for ScreenshotRun Screenshot API.

Features

  • Capture screenshots of any public webpage as PNG, JPEG, WebP, or PDF

  • Render raw HTML or Markdown to image

  • Device emulation — desktop, mobile, and tablet viewports

  • Dark mode rendering with prefers-color-scheme: dark

  • Full-page capture with automatic scrolling

  • Block ads, cookie consent banners, and live chat widgets

  • Inject custom CSS/JavaScript before capture

  • Target specific elements with CSS selectors

  • Wait for elements, click, hover, and scroll before capture

  • Retina (2x) and custom device pixel ratio support

  • Geolocation and timezone emulation

  • Stealth mode to avoid bot detection

  • Transparent background, clipping, and output resizing

  • Extract page metadata (title, description, OG tags, Twitter Card)

  • Analyze page structure — headings, interactive elements, forms, images, navigation with bounding rectangles

  • Certified screenshots with SHA-256 hash

  • PDF output with custom page format and margins

  • Scroll video recording

  • Monitor your API usage and remaining quota

Related MCP server: ShotAPI

Quick Start

1. Get your API key

Sign up for a free API key at screenshotrun.com.

2. Configure your AI client

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "screenshotrun": {
      "command": "npx",
      "args": ["-y", "screenshotrun-mcp"],
      "env": {
        "SCREENSHOTRUN_API_KEY": "sr_live_your_key_here"
      }
    }
  }
}

Claude Code

claude mcp add screenshotrun \
  npx -y screenshotrun-mcp \
  -e SCREENSHOTRUN_API_KEY=sr_live_your_key_here

Cursor

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "screenshotrun": {
      "command": "npx",
      "args": ["-y", "screenshotrun-mcp"],
      "env": {
        "SCREENSHOTRUN_API_KEY": "sr_live_your_key_here"
      }
    }
  }
}

Windsurf / VS Code

Add to your MCP configuration with the same npx -y screenshotrun-mcp command and set the SCREENSHOTRUN_API_KEY environment variable.

Available Tools

take_screenshot

Capture a screenshot of any webpage, raw HTML, or Markdown. Returns the image as base64-encoded data that AI agents can analyze and describe.

Source (one required)

Parameter

Type

Description

url

string

URL to screenshot (http:// or https://)

html

string

Raw HTML to render (max 500KB)

markdown

string

Markdown to render (max 500KB)

Output

Parameter

Type

Default

Description

format

png | jpeg | webp | pdf

png

Output format

quality

number

80

Image quality for JPEG/WebP (1-100)

Viewport & Device

Parameter

Type

Default

Description

width

number

1280

Viewport width (320-3840)

height

number

800

Viewport height (200-2160)

full_page

boolean

false

Capture entire scrollable page

device

desktop | mobile | tablet

--

Device preset

retina

boolean

false

2x resolution

device_scale_factor

number

--

Custom pixel ratio (0.5-4)

Appearance

Parameter

Type

Default

Description

dark_mode

boolean

false

Enable dark mode

omit_background

boolean

false

Transparent background (PNG/WebP)

media_type

screen | print

--

Emulate CSS media type

reduced_motion

boolean

false

Emulate prefers-reduced-motion

disable_animations

boolean

false

Disable CSS animations

Blocking

Parameter

Type

Default

Description

block_ads

boolean

false

Block advertisements

block_cookies

boolean

true

Block cookie consent dialogs

block_chats

boolean

false

Block live chat widgets

block_requests

string[]

--

URL patterns to block

block_resources

string[]

--

Resource types to block (image, stylesheet, font, script, media, websocket, manifest, other)

Interaction

Parameter

Type

Description

selector

string

CSS selector to capture a specific element

click_selector

string

Element to click before capture

hover_selector

string

Element to hover before capture

scroll_to

string

Element to scroll into view

hide_selectors

string[]

Elements to hide before capture

wait_for_selector

string

Wait for element to appear

Injection

Parameter

Type

Description

css

string

Custom CSS (max 10KB)

js

string

Custom JavaScript (max 10KB)

user_agent

string

Custom User-Agent

headers

object

Custom HTTP headers

cookies

array

Cookies to set ({name, value, domain?})

Timing

Parameter

Type

Default

Description

delay

number

0

Seconds to wait after load (0-10)

timeout

number

30

Max page load time (5-60s)

navigation_timeout

number

--

Max navigation time (5-60s)

wait_until

string

--

load, domcontentloaded, networkidle, or commit

Clipping & Resizing

Parameter

Type

Description

resize_width

number

Resize output width (16-3840)

resize_height

number

Resize output height (16-2160)

clip

object

Clip rectangle {x, y, width, height}

Advanced

Parameter

Type

Default

Description

stealth

boolean

false

Stealth mode (avoid bot detection)

bypass_csp

boolean

false

Bypass Content Security Policy

cache_ttl

number

--

Cache duration in seconds (0-86400)

extract_metadata

boolean

false

Extract page metadata (title, OG, Twitter Card)

certified

boolean

false

Certified screenshot with SHA-256

Geolocation

Parameter

Type

Description

geolocation

object

{latitude, longitude, accuracy?}

timezone

string

e.g. America/New_York

proxy

string

HTTP/SOCKS proxy URL

PDF Options (format=pdf)

Parameter

Type

Description

pdf_landscape

boolean

Landscape orientation

pdf_page_format

string

A3, A4, A5, Letter, Legal, Tabloid

pdf_margin_top

string

e.g. 1cm, 0.5in

pdf_margin_right

string

Right margin

pdf_margin_bottom

string

Bottom margin

pdf_margin_left

string

Left margin

Scroll Video

Parameter

Type

Description

scroll_video

boolean

Record scrolling video

scroll_duration

number

Duration 2-30 seconds

scroll_speed

slow | medium | fast

Scroll speed

analyze_page

Analyze any webpage and get structured data about its content. Returns headings, interactive elements (buttons, links, inputs), forms, images, and navigation links — each with a bounding rectangle [x, y, width, height] for visual mapping. Pro feature with 20 free trial runs per month.

Core Parameters

Parameter

Type

Default

Description

url

string

required

URL to analyze (http:// or https://)

include

string[]

all

Categories to return: headings, interactive, forms, images, text, navigation

visible_only

boolean

true

Only return visible elements

scope

string

--

CSS selector to limit analysis to a section (e.g. main, #content)

with_screenshot

boolean

false

Capture screenshot alongside analysis (costs 1 extra request)

Viewport & Appearance

Parameter

Type

Default

Description

width

number

1280

Viewport width (320-3840)

height

number

800

Viewport height (200-2160)

device

desktop | mobile | tablet

--

Device preset

dark_mode

boolean

false

Enable dark mode

Blocking & Timing

Parameter

Type

Default

Description

block_ads

boolean

false

Block advertisements

block_cookies

boolean

true

Block cookie consent dialogs

block_chats

boolean

false

Block live chat widgets

delay

number

0

Seconds to wait after load (0-10)

timeout

number

30

Max page load time (5-60s)

stealth

boolean

false

Stealth mode

Injection & Advanced

Parameter

Type

Description

css

string

Custom CSS (max 10KB)

js

string

Custom JavaScript (max 10KB)

hide_selectors

string[]

Elements to hide before analysis

wait_for_selector

string

Wait for element to appear

user_agent

string

Custom User-Agent

proxy

string

HTTP/SOCKS proxy URL

timezone

string

e.g. America/New_York

geolocation

object

{latitude, longitude, accuracy?}

headers

object

Custom HTTP headers

cookies

array

Cookies to set ({name, value, domain?})

extract_content

Extract page metadata from any URL without downloading the full image. Returns title, description, Open Graph tags, Twitter Card tags, favicon URL, and HTTP status. Useful for SEO audits, content analysis, and link previews.

Parameter

Type

Description

url

string

URL to extract metadata from

check_usage

Check your ScreenshotRun API usage for the current billing period. Returns screenshots used, remaining quota, usage percentage, and days remaining.

No parameters required.

Example Prompts

  • "Take a screenshot of screenshotrun.com"

  • "Screenshot stripe.com on mobile in dark mode"

  • "Capture full-page screenshot of my website in WebP"

  • "Take a retina screenshot of example.com in JPEG format"

  • "Screenshot a page with the cookie banner and chat widget hidden"

  • "Render this HTML as an image: <h1>Hello World</h1>"

  • "Capture example.com as seen from Tokyo" (with geolocation + timezone)

  • "Take a screenshot with transparent background for my design comp"

  • "Wait for the .loading-spinner to disappear, then screenshot"

  • "Click the 'Show More' button, then capture the page"

  • "Analyze the page structure of competitor.com — show me all headings and interactive elements"

  • "What forms and images are on this landing page?"

  • "Analyze example.com on mobile and show me the navigation links"

  • "Extract the OG tags and meta description from competitor.com"

  • "Check how many screenshots I have left this month"

How It Works

  1. Your AI agent receives a user request involving a webpage

  2. The agent calls the appropriate tool (take_screenshot, analyze_page, or extract_content)

  3. The MCP server sends the request to the ScreenshotRun API

  4. The API renders the page in a real browser and returns the result

  5. Screenshots are returned as base64 images; analysis results are returned as structured text with element positions

Requirements

Other Projects by ScreenshotRun

  • SnapshotArchive — Automated website monitoring with visual diff detection

  • WatchCron — Cron job & heartbeat monitoring for developers

License

MIT

Available Tools

2 tools
check_usageA

Check your ScreenshotRun API usage for the current billing period. Shows screenshots used, remaining, and limits.

NameRequiredDescriptionDefault

No parameters

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It discloses the read-only nature ('Check'), the temporal scope (current billing period), and the returned fields, but says nothing about auth requirements, rate limits, or whether usage is real-time.

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?

Two short sentences, front-loaded with the action and scope, followed by the concrete return content. No waste.

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 a zero-parameter read-only tool with no output schema, the description is largely complete: it explains what is queried and what is returned. Minor gap is lack of auth/real-time context, but nothing needed to invoke it correctly is missing.

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

Parameters4/5

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

Zero parameters, so there is nothing to document; baseline is 4. The description correctly requires no input, matching the empty schema.

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

Purpose4/5

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

States a specific verb (check) and resource (API usage) plus the scope (current billing period) and what is shown (screenshots used, remaining, limits). It is unambiguous what it does, though it does not explicitly name or distinguish itself from the sibling take_screenshot.

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

Usage Guidelines3/5

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

Usage is implied by 'current billing period' — the agent infers this is a read-only status check. There is no explicit statement of when to use it, no exclusions, and no mention of the sibling, so guidance is implied rather than stated.

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

take_screenshotA

Capture a screenshot of any webpage. Returns the image as base64-encoded data. Supports custom viewport sizes, device emulation, dark mode, full-page capture, ad blocking, and more.

NameRequiredDescriptionDefault
jsNoCustom JavaScript to execute before capture
cssNoCustom CSS to inject into the page
urlYesURL of the page to screenshot (must start with http:// or https://)
delayNoDelay in seconds after page load before capturing
widthNoViewport width in pixels
deviceNoDevice preset (affects viewport and user agent)
formatNoOutput image formatpng
heightNoViewport height in pixels
retinaNoCapture at 2x resolution (retina)
qualityNoImage quality for JPEG/WebP (1-100)
selectorNoCSS selector to capture a specific element instead of the full viewport
block_adsNoBlock advertisements during capture
dark_modeNoEnable dark mode (prefers-color-scheme: dark)
full_pageNoCapture the entire scrollable page
scroll_toNoCSS selector of an element to scroll into view before capture
block_cookiesNoBlock cookie consent dialogs
click_selectorNoCSS selector of an element to click before capture
hide_selectorsNoCSS selectors of elements to hide before capture

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are provided, so the description carries the behavioral burden. It usefully discloses that the result is base64-encoded image data and mentions several feature areas, but it does not disclose important behavioral traits such as permissions, rate limits, timeout behavior, or the fact that custom JS and click actions can affect the target page.

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

Conciseness4/5

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

The description is short and front-loads the core action and return format. The phrase 'and more' is slightly vague, but overall the structure is efficient and appropriately sized for a tool whose parameter details are covered by the schema.

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

Completeness3/5

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

For an 18-parameter tool with no annotations and no output schema, the description is adequate but not fully complete. It explains the return value and major capabilities, but it does not cover behavioral context such as side effects from JS execution, rate limits, or error conditions.

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 the input schema already documents all 18 parameters, including url, viewport, format, and selectors. The description highlights a subset of capabilities such as viewport sizes, device emulation, dark mode, and full-page capture, but adds no syntax or format detail beyond what the schema provides.

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?

The description states a specific verb and resource: 'Capture a screenshot of any webpage.' It also clarifies the return format as base64-encoded image data. The purpose is unambiguous and distinct from the unrelated sibling check_usage.

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

Usage Guidelines3/5

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

The description implies usage by saying it captures 'any webpage' and listing supported features, but it gives no explicit when-to-use guidance, prerequisites, or exclusions. Since the only sibling is check_usage, there is no alternative screenshot tool to compare against, but the guidance remains implied rather than stated.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.3
    • First observedcheck_usage
    • First observedtake_screenshot
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 2 tools

Disambiguation5/5

The two tools serve completely different purposes: one queries billing/quota usage, the other performs screenshot capture. There is no plausible way an agent would confuse them.

Naming Consistency5/5

Both tools follow the same snake_case verb_noun convention (check_usage, take_screenshot), making the pattern predictable and readable.

Tool Count4/5

Two tools is thin but defensible for a focused screenshot API wrapper—capture plus quota check are the core operations. It sits just below the typical 3+ range, so not a full 5.

Completeness4/5

The essential workflow (take a screenshot, check remaining quota) is covered, but there is no way to retrieve previously captured screenshots, list history, or manage account settings. These are minor gaps agents can work around for the primary use case.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues

Resources

Related MCP Connectors

Related MCP Servers