This record as markdown: /tools/com-geekflare-mcp/screenshot.md
What screenshot does on Mcp
AI agents call screenshot to retrieve information from Mcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | Yes | Target URL |
type | string | — | |
delay | number | — | Seconds to wait before screenshot |
theme | string | — | Color scheme to render before capturing |
device | string | — | |
inline | boolean | — | Return image data inline instead of a CDN URL |
quality | number | — | Image quality for JPEG/WEBP |
blockAds | boolean | — | |
fullPage | boolean | — | |
selector | string | — | CSS selector of the element to capture, instead of the full viewport/page |
hideCookie | boolean | — | Hide cookie consent banners |
pageHeight | number | — | Height of page for partial screenshot |
Parameters from the server's own tool schema.
Why screenshot is rated Low
The tool reads/renders a public webpage and returns an image. It does not modify any data, execute arbitrary code, or have financial implications. Misuse potential is low since it only captures what is publicly visible.
From the tool's definition 'Capture a screenshot of a website' — retrieves a visual snapshot of a webpage with no side effects
Risk signalsAccepts URL/endpoint input (url) · High parameter count (23 properties)
Attacks that exploit this kind of access
The rule that runs screenshot safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For screenshot, this is the rule to start with:
screenshot is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mcp, apply this rule, and every screenshot call is checked against it from then on.
Questions about screenshot
Capture a screenshot of a website. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
screenshot accepts 12 parameters: url, type, delay, theme, device, inline, quality, blockAds, fullPage, selector, hideCookie, pageHeight. Required: url. The full parameter table on this page comes from the server's own tool schema.
Register the MCP server in PolicyLayer and add a rule for screenshot: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the screenshot rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for screenshot. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
screenshot is provided by the MCP server (@geekflare/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on , and thousands of servers like it.
This server
Across the catalogue