Unstuck

Screenshot a Web Page

screenshot

Read-only

Take a screenshot of a website. Open any web page URL in a real browser and capture it as a PNG image, either the visible area or the full page. Use it to see what a site looks like, check a page layout, or capture visual proof of a web page. Price: $0.01 per successful call; failed calls are free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "screenshot"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	The http(s) URL of the web page to capture.
`width`	No	Viewport width in pixels (default 1280).
`height`	No	Viewport height in pixels (default 800).
`api_key`	No	Your Unstuck API key, if this connection has none. Leave empty to try free tools or to get a key and payment link.
`full_page`	No	Capture the whole scrollable page instead of just the viewport (capped at 10000px tall).

Output Schema

Name	Required	Description
`url`	Yes	Link to the PNG, valid for 24 hours.
`bytes`	Yes	PNG size in bytes.
`title`	Yes	Page title.
`width`	Yes	Viewport width used, in pixels.
`final_url`	Yes	Page URL after redirects.
`expires_at`	Yes	When the link expires (ISO 8601).
`balance_usd`	Yes	Remaining prepaid balance, USD.
`charged_usd`	Yes	Amount charged for this call, USD.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 4, 2026

addedInput schema / properties / api_key

Added value: +{
+  "description": "Your Unstuck API key, if this connection has none. Leave empty to try free tools or to get a key and payment link.",
+  "maxLength": 200,
+  "type": "string"
+}

First observedOct 4, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, openWorld, non-idempotent, non-destructive, so the safety profile is covered. The description adds genuinely new context beyond that: the pricing model ($0.01 per successful call, failed calls free) and the fact it uses a real browser, both operationally relevant. It doesn't mention rate limits or latency.

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?

Four tight sentences with the core action and output front-loaded, followed by use cases and cost. No filler; every sentence carries information an agent can act on.

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?

With an output schema present the return format needn't be described, and the description covers action, use cases, auth (via the api_key param), and cost. Slightly incomplete on failure/pagination behavior for a paid external call, but otherwise self-contained.

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?

Schema coverage is 100%, so parameters are self-documented and the baseline is 3. The description adds meaning beyond the schema by explaining the viewport-vs-full-page choice ('either the visible area or the full page'), reinforcing the full_page flag's purpose.

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 (take a screenshot of a website, open any web page URL in a real browser) and names the output artifact (PNG image), with the viewport/full-page distinction. The 'capture as image' framing cleanly separates it from text-oriented siblings like read_page and web_search.

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?

Gives clear use cases ('see what a site looks like, check a page layout, or capture visual proof'), which tells the agent when this tool fits. It stops short of naming alternatives (e.g., use read_page for extractable text) or stating when-not to use it.

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

All Unstuck tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?