Skip to main content
Glama
Sign In
CaptureKit MCP Server

CaptureKit MCP Server

Official
by capturekitdev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Capture (Screenshot)

capture
Read-only

Take webpage screenshots or PDFs in PNG, JPEG, or WebP with full-page, viewport, delay, and element options for previews, QA, reporting, monitoring, and archiving.

Instructions

Capture (Screenshot). Browser-like Screenshot API that captures webpages as PNG/JPEG/WebP or PDF for previews, QA, reporting, monitoring, and archiving no headless setup. Credit cost: 1 credit per call.

Input Schema

NameRequiredDescriptionDefault
urlYesThe URL of the webpage to capture. Examples: https://www.amazon.com/s?k=pokemon
cacheNoCache the response. Default: false.
delayNoDelay in seconds before capturing the screenshot. Default: 0.
proxyNoSpecify a proxy server to route your request through.
deviceNoThe device type to emulate for the screenshot. Allowed values: galaxy_fold4, galaxy_s23, galaxy_s23_ultra, galaxy_s8, huawei_mate_50_pro, huawei_p60_pro, ipad, iphone_12, iphone_13_mini, iphone_13_pro_max, iphone_14_pro, iphone_14_pro_max, iphone_x, pixel_5, pixel_6a, pixel_7_pro, redmi_note_11, redmi_note_12_pro.
fieldsNoComma-separated list of fields to keep in the response, with dot notation for nested fields (e.g. name,location.city). Does not change the credit cost.
formatNoThe output format of the screenshot. Allowed values: jpeg, jpg, pdf, png, webp. Default: "png".
s3_urlNoUse S3 storage for screenshots. The S3 URL will be returned in the response. Default: false.
selectorNoCapture a specific element on the page instead of the full viewport.
cache_ttlNoCache the response for a custom TTL (in seconds). Default: 2592000.
full_pageNoCapture the entire page instead of just the visible viewport. Default: false.
s3_bucketNoThe S3 bucket name where the screenshot will be uploaded.
s3_regionNoAWS S3 region for storage.
block_urlsNoComma-separated list of URL patterns to block (e.g., “analytics,tracking,advertisement”).
remove_adsNoAutomatically remove ads before capturing. Default: false.
wait_untilNoDefine when to capture. Allowed values: domcontentloaded, load, networkidle0, networkidle2.
scale_factorNoThe scale factor for high-resolution screenshots. Default: 1.
image_qualityNoGenerate images with custom quality settings. Default: "80".
s3_object_keyNoThe filename for the S3 object (auto-generated if not provided).
s3_secret_keyNoAWS S3 secret access key.
viewport_widthNoThe width of the browser viewport in pixels. Default: 1280.
block_resourcesNoComma-separated list of resource types to block (e.g., “image,stylesheet,font”). Allowed values: document, eventsource, fetch, font, image, manifest, media, other, script, stylesheet, texttrack, websocket, xhr.
viewport_heightNoThe height of the browser viewport in pixels. Default: 1024.
full_page_scrollNoScroll the page to fully load lazy-loaded elements before capturing a full-page screenshot. Default: false.
remove_selectorsNoA comma-separated list of elements to hide before capturing (e.g., ads, popups).
s3_access_key_idNoAWS S3 access key ID.
storage_endpointNoLeave this field empty for AWS S3. Only specify a value if required. S3-compatible storage services are supported, for example, use https://<accountId>.r2.cloudflarestorage.com for Cloudflare R2.
wait_for_selectorNoWait for a specific element to appear before taking the screenshot.
remove_cookie_bannersNoAutomatically remove cookie banners before capturing. Default: false.
full_page_scroll_durationNoTime in milliseconds for scrolling before capturing the full page. Default: 400.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description usefully adds the cost model ('1 credit per call') and the managed-browser convenience, but says nothing about what is actually returned (inline image vs. hosted URL), latency, or failure behavior on unreachable pages.

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?

Two tight sentences with the core capability front-loaded and the cost note at the end where it belongs. The leading 'Capture (Screenshot).' duplicates the title, which is minor waste, but nothing else is padded.

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 a 30-parameter tool with no output schema, the description is thin: it never states whether the response contains image bytes, a URL, or an S3 link, which is the single most important omission for a capture API. The rich schema compensates for parameter knowledge but not for return-value expectations.

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% across all 30 parameters, so the schema does the heavy lifting and the baseline of 3 applies. The description adds no parameter-level meaning of its own and merely restates the supported output formats already enumerated in the format field.

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?

The description names a specific verb and resource ('captures webpages as PNG/JPEG/WebP or PDF') and lists concrete output formats, so the tool's function is unambiguous. It does not, however, distinguish this tool from siblings like content, analyze, or website_crawler, which arguably also touch a URL.

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?

Use cases are listed (previews, QA, reporting, monitoring, archiving) and 'no headless setup' hints at why to choose this over rolling your own. But there is no explicit when-not guidance and no reference to the sibling tools or when website_crawler/analyze would be the better pick.

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

Deploy Server

Other Tools