ui_annotated_screenshot
AI agents call ui_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.
Screenshot and annotation capture visual state without modifying data or triggering external operations. Classified as Read because it retrieves UI information for inspection purposes. Severity is low due to minimal blast radius—screenshots may expose sensitive UI state but do not execute commands, delete data, or move money.
From the tool's definition Tool name 'ui_annotated_screenshot' indicates screenshot capture and annotation—a read-only inspection action. Server context describes 'inspect and interact with UI elements' in both control and SDK modes. No side effects or modifications are suggested.
Attacks that exploit this kind of access
ui_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 ui_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.
ui_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 ui_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 ui_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.
ui_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 →