AI agents call ui_diff_check to retrieve information from Vison-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs visual comparison analysis on provided screenshots, outputting differences without side effects. It reads and analyzes image data but does not create, modify, delete, or execute operations.
From the tool's definition Tool name 'ui_diff_check' and description 'Compare two UI screenshots — design vs implementation — to identify visual differences' indicate a comparison/analysis operation that retrieves and processes image data without modifying, deleting, or executing code.
Attacks that exploit this kind of access
Compare two UI screenshots — design vs implementation — to identify visual differences,. It is categorised as a Read tool in the Vison-MCP MCP Server, which means it retrieves data without modifying state.
Register the Vison- MCP server in PolicyLayer and add a rule for ui_diff_check: 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 Vison-MCP. Nothing to install.
ui_diff_check 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_diff_check 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_diff_check. 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_diff_check is provided by the Vison- MCP server (lin-zhibo/vison-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 →