take_screenshot

Capture screenshot of current page/screen

Server Web Bridge @midscene/web-bridge-mcp
Category Read
Risk class Low
Parameters 50 required

What take_screenshot does on Web Bridge

AI agents call take_screenshot to retrieve information from Web Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
web.url string URL to open in new tab (omit to use current page)
web.aiActContext string Background knowledge passed to aiAct. Default: no extra context.
web.waitAfterAction number Wait time in milliseconds after each action execution. Default: 300ms.
web.replanningCycleLimit integer Maximum number of replanning cycles for aiAct. Default: model adapter default.
web.screenshotShrinkFactor number Screenshot shrink factor before sending images to AI. Default: 1; high values may reduce recognition quality, especially on mobile.

Parameters from the server's own tool schema.

Why take_screenshot needs a policy

Taking a screenshot captures the current state of a page or screen. This is a passive observation action with no side effects, no code execution, no data modification, and no destructive impact. It belongs in the Read category with low severity, as screenshots themselves do not cause harmful effects even if captured by an AI agent, though they may reveal sensitive visual information.

From the tool's definition "Capture screenshot of current page/screen" - this is a read-only operation that retrieves visual data without modifying, executing, deleting, or moving any resources.

Risk signalsAccepts URL/endpoint input (web.url)

Questions about take_screenshot

What does the take_screenshot tool do? +

Capture screenshot of current page/screen. It is categorised as a Read tool in the Web Bridge MCP Server, which means it retrieves data without modifying state.

What parameters does take_screenshot accept? +

take_screenshot accepts 5 parameters: web.url, web.aiActContext, web.waitAfterAction, web.replanningCycleLimit, web.screenshotShrinkFactor. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on take_screenshot? +

Register the Web Bridge MCP server in PolicyLayer and add a rule for take_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 Web Bridge. Nothing to install.

What risk level is take_screenshot? +

take_screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit take_screenshot? +

Yes. Add a rate_limit block to the take_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.

How do I block take_screenshot completely? +

Set action: deny in the PolicyLayer policy for take_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.

What MCP server provides take_screenshot? +

take_screenshot is provided by the Web Bridge MCP server (@midscene/web-bridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.