Save a snapshot bookmark for later diffing in the runner
AI agents use ui_save_bookmark to create or update resources in UI Bridge MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UI Bridge MCP environment.
The tool creates new data (a bookmark/snapshot) in a reversible manner—bookmarks can be deleted or replaced—with no destructive, financial, or code-execution side effects. This is a pure data-creation operation, making it Write category. Severity is low because bookmarks are non-critical metadata with minimal blast radius if misused.
From the tool's definition Tool name 'ui_save_bookmark' and description 'Save a snapshot bookmark' indicate the tool creates/stores a bookmark artifact (snapshot state) that persists for later comparison.
Attacks that exploit this kind of access
Save a snapshot bookmark for later diffing in the runner. It is categorised as a Write tool in the UI Bridge MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the UI Bridge MCP server in PolicyLayer and add a rule for ui_save_bookmark: 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_save_bookmark is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the ui_save_bookmark 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_save_bookmark. 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_save_bookmark 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 →