sdk_annotated_screenshot
AI agents call sdk_annotated_screenshot to retrieve information from UI Bridge MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or query visual state of UI elements (screenshot with annotations) without causing side effects. The 'sdk_' prefix indicates SDK mode for external application inspection. Screenshot capture is a read-only operation. Confidence is reduced from 0.85 to 0.75 due to the empty tool description, though the name and server context provide reasonable inferential support.
From the tool's definition Tool name 'sdk_annotated_screenshot' suggests visual inspection/capture of UI elements. Server description indicates it 'inspect[s]' UI elements.
Attacks that exploit this kind of access
sdk_annotated_screenshot. It is categorised as a Read tool in the UI Bridge MCP MCP Server, which means it retrieves data without modifying state.
Register the UI Bridge MCP server in PolicyLayer and add a rule for sdk_annotated_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 UI Bridge MCP. Nothing to install.
sdk_annotated_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 sdk_annotated_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 sdk_annotated_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.
sdk_annotated_screenshot is provided by the UI Bridge MCP server (qontinui/ui-bridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the 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 →