PageShot

take_screenshot

Take a screenshot of any webpage. Returns a base64-encoded image.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The URL to screenshot
`delay`	No	Delay in ms before capture
`width`	No	Viewport width (default: 1280)
`clip_x`	No	Clip region X offset in pixels
`clip_y`	No	Clip region Y offset in pixels
`format`	No	Image format (default: png)
`height`	No	Viewport height (default: 720)
`locale`	No	BCP 47 locale tag for the browser context (e.g., "en-US", "de-DE", "ja-JP")
`cookies`	No	Cookies to set before capture (e.g., [{"name": "session", "value": "abc123"}])
`headers`	No	Custom HTTP headers to send with the request (e.g., {"Authorization": "Bearer token"})
`quality`	No	Image quality 1-100 (default: 80)
`evaluate`	No	JavaScript code to execute on the page before capture (max 10KB). Runs in the browser context via page.evaluate(). Use to dismiss modals, click buttons, or set UI state.
`latitude`	No	Geolocation latitude (-90 to 90). Must be used with longitude.
`selector`	No	CSS selector to capture specific element
`timezone`	No	IANA timezone for the browser context (e.g., "America/New_York", "Europe/Berlin", "Asia/Tokyo")
`dark_mode`	No	Enable dark mode emulation
`full_page`	No	Capture full page scroll height
`longitude`	No	Geolocation longitude (-180 to 180). Must be used with latitude.
`clip_width`	No	Clip region width in pixels
`wait_until`	No	Page load strategy: "commit" (fastest, response received), "domcontentloaded" (default, DOM ready), "load" (all resources loaded), "networkidle" (no network activity for 500ms — best for SPAs and lazy-loaded content)
`clip_height`	No	Clip region height in pixels
`hide_banners`	No	Dismiss cookie banners, consent popups, and overlays before capture
`resize_width`	No	Resize output image to this width (maintains aspect ratio)
`resize_height`	No	Resize output image to this height (maintains aspect ratio)
`disable_javascript`	No	Disable JavaScript execution on the page. Useful for security research, capturing static HTML, or avoiding JS-driven redirects.
`ignore_https_errors`	No	Ignore HTTPS/TLS certificate errors (useful for dev/staging environments with self-signed certs)

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedMar 13, 2026

addedInput schema / properties / ignore_https_errors

Added value: +{
+  "description": "Ignore HTTPS/TLS certificate errors (useful for dev/staging environments with self-signed certs)",
+  "type": "boolean"
+}

addedInput schema / properties / wait_until

Added value: +{
+  "description": "Page load strategy: \"commit\" (fastest, response received), \"domcontentloaded\" (default, DOM ready), \"load\" (all resources loaded), \"networkidle\" (no network activity for 500ms — best for SPAs and lazy-loaded content)",
+  "enum": [
+    "commit",
+    "domcontentloaded",
+    "load",
+    "networkidle"
+  ],
+  "type": "string"
+}

Changed3 schema fields changedMar 11, 2026

addedInput schema / properties / disable_javascript

Added value: +{
+  "description": "Disable JavaScript execution on the page. Useful for security research, capturing static HTML, or avoiding JS-driven redirects.",
+  "type": "boolean"
+}

addedInput schema / properties / latitude

Added value: +{
+  "description": "Geolocation latitude (-90 to 90). Must be used with longitude.",
+  "maximum": 90,
+  "minimum": -90,
+  "type": "number"
+}

addedInput schema / properties / longitude

Added value: +{
+  "description": "Geolocation longitude (-180 to 180). Must be used with latitude.",
+  "maximum": 180,
+  "minimum": -180,
+  "type": "number"
+}

Changed2 schema fields changedMar 10, 2026

addedInput schema / properties / locale

Added value: +{
+  "description": "BCP 47 locale tag for the browser context (e.g., \"en-US\", \"de-DE\", \"ja-JP\")",
+  "type": "string"
+}

addedInput schema / properties / timezone

Added value: +{
+  "description": "IANA timezone for the browser context (e.g., \"America/New_York\", \"Europe/Berlin\", \"Asia/Tokyo\")",
+  "type": "string"
+}

Changed5 schema fields changedMar 9, 2026

addedInput schema / properties / clip_height

Added value: +{
+  "description": "Clip region height in pixels",
+  "minimum": 1,
+  "type": "number"
+}

addedInput schema / properties / clip_width

Added value: +{
+  "description": "Clip region width in pixels",
+  "minimum": 1,
+  "type": "number"
+}

addedInput schema / properties / clip_x

Added value: +{
+  "description": "Clip region X offset in pixels",
+  "minimum": 0,
+  "type": "number"
+}

addedInput schema / properties / clip_y

Added value: +{
+  "description": "Clip region Y offset in pixels",
+  "minimum": 0,
+  "type": "number"
+}

addedInput schema / properties / evaluate

Added value: +{
+  "description": "JavaScript code to execute on the page before capture (max 10KB). Runs in the browser context via page.evaluate(). Use to dismiss modals, click buttons, or set UI state.",
+  "type": "string"
+}

Changed2 schema fields changedMar 8, 2026

addedInput schema / properties / cookies

Added value: +{
+  "description": "Cookies to set before capture (e.g., [{\"name\": \"session\", \"value\": \"abc123\"}])",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "name": {
+        "type": "string"
+      },
+      "path": {
+        "type": "string"
+      },
+      "value": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "name",
+      "value"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / headers

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "description": "Custom HTTP headers to send with the request (e.g., {\"Authorization\": \"Bearer token\"})",
+  "type": "object"
+}

Changed3 schema fields changedMar 7, 2026

addedInput schema / properties / hide_banners

Added value: +{
+  "description": "Dismiss cookie banners, consent popups, and overlays before capture",
+  "type": "boolean"
+}

addedInput schema / properties / resize_height

Added value: +{
+  "description": "Resize output image to this height (maintains aspect ratio)",
+  "maximum": 2160,
+  "minimum": 16,
+  "type": "number"
+}

addedInput schema / properties / resize_width

Added value: +{
+  "description": "Resize output image to this width (maintains aspect ratio)",
+  "maximum": 3840,
+  "minimum": 16,
+  "type": "number"
+}

First observedFeb 18, 2026

TDQS

B3.3/5.0

Behavior3/5

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

The description discloses the return format (base64-encoded image), which is useful. However, with no annotations provided, the description carries the full burden for behavioral disclosure. It does not mention that the tool loads a webpage, executes JavaScript, or may handle cookies, popups, or geolocation—though these are hinted at in the schema.

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?

The description is two sentences with zero padding. It front-loads the purpose and includes the essential return type, achieving maximum efficiency.

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?

Given the tool's complexity (26 parameters, no annotations, no output schema), the description is minimally adequate but lacks high-level context. It tells what the tool does and returns, but does not help the agent choose among siblings or anticipate behavior like page loading or execution context.

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?

The input schema has 100% description coverage across all 26 parameters, so the schema does the heavy lifting. The description adds no additional parameter meaning beyond confirming a URL is required, which is already stated in the 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?

The verb 'take' and resource 'screenshot of any webpage' clearly state the tool's primary function. It is concise and unambiguous, though it does not explicitly differentiate itself from siblings like batch_screenshot or render_html.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. There is no mention of scenarios, exclusions, or sibling comparison, leaving the agent to infer usage context from the name alone.

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

All PageShot tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0

Disambiguation4/5

take_screenshot and batch_screenshot both capture screenshots, but batch_screenshot handles multiple URLs while take_screenshot handles a single page, making them distinct enough. render_html and generate_pdf are clearly separate (image vs. PDF, HTML input vs. URL/HTML). Minor confusion possible between the two screenshot tools.

Naming Consistency4/5

Three tools follow the verb_noun pattern (take_screenshot, generate_pdf, render_html), but batch_screenshot breaks the pattern by leading with an adjective/noun rather than a verb. The inconsistency is minor and the names remain readable.

Tool Count5/5

Four tools is well-scoped for a page capture server. Each tool covers a distinct use case: single screenshot, batch screenshot, HTML rendering to image, and PDF generation. No redundancy or excessive bloat.

Completeness4/5

The set covers core web capture needs: single page screenshots, batch captures, HTML/CSS to image, and PDF conversion. Minor gaps include no explicit full-page screenshot option or advanced viewport control, but common workflows are supported.

Resources

Need Help?