sdk_visual_description
AI agents call sdk_visual_description 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.
The tool appears designed to extract or describe visual UI elements from a screen. Even without explicit documentation, the naming convention ('visual_description') and positioning among other SDK analysis tools indicate this is an informational read operation with no side effects. Empty description lowers confidence slightly, but semantic context supports Read classification.
From the tool's definition Tool name 'sdk_visual_description' and server context indicate it retrieves visual/UI information. Description is empty, but naming pattern and sibling tools (sdk_analyze_data, sdk_annotated_screenshot) suggest data retrieval without modification.
Attacks that exploit this kind of access
sdk_visual_description. 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_visual_description: 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_visual_description 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_visual_description 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_visual_description. 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_visual_description 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 →