sdk_page_go_back
AI agents invoke sdk_page_go_back to trigger actions in UI Bridge MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Navigating back in a browser or UI context is an Execute-class action as it triggers an external UI operation. The empty description prevents full certainty, but the naming pattern on this server (sdk_ prefix with UI interaction tools like sdk_ai_execute) strongly implies it performs a navigation action rather than merely reading data.
From the tool's definition Tool name 'sdk_page_go_back' suggests triggering a browser/UI navigation action (going back a page), which is an external operation. Description is empty, lowering confidence.
Attacks that exploit this kind of access
sdk_page_go_back. It is categorised as a Execute tool in the UI Bridge MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the UI Bridge MCP server in PolicyLayer and add a rule for sdk_page_go_back: 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_page_go_back is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sdk_page_go_back 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_page_go_back. 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_page_go_back 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 →