AI agents call visual_test_reporting to retrieve information from InSite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool collects and formats existing visual test data (screenshots, comparisons) into reports. It does not modify browser state, create destructive changes, or trigger external operations with side effects. While it is part of a browser automation server, the specific function here is retrospective reporting on captured visuals, making it a Read operation with low severity.
From the tool's definition Tool generates and reports visual test data without modifying or deleting underlying state. The description indicates 'Generate comprehensive visual test reports with image galleries' — a data aggregation and presentation function.
Attacks that exploit this kind of access
Generate comprehensive visual test reports with image galleries. It is categorised as a Read tool in the InSite MCP Server, which means it retrieves data without modifying state.
Register the InSite MCP server in PolicyLayer and add a rule for visual_test_reporting: 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 InSite. Nothing to install.
visual_test_reporting 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 visual_test_reporting 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 visual_test_reporting. 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.
visual_test_reporting is provided by the InSite MCP server (jowharshamshiri/insite). 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 →