sdk_save_bookmark · UI Bridge MCP: Risk & Policy

WHAT IT DOES

What sdk_save_bookmark does on UI Bridge MCP

AI agents use sdk_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.

WHY IT NEEDS A POLICY

Why sdk_save_bookmark needs a policy

This tool creates a new bookmark record (a snapshot of UI state) in a reversible manner. It has no destructive capability, does not execute external code/commands, does not delete data, and does not move money. The impact is limited to recording UI state for later comparison, making it a Write operation with low severity since bookmarks can be deleted or overwritten without lasting harm.

From the tool's definition The tool 'sdk_save_bookmark' is described as 'Save a snapshot bookmark for later diffing. Captures current UI state.' The verb 'Save' indicates data creation/modification; bookmarks are reversibly created and managed artifacts.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sdk_save_bookmark Rate-limited

sdk_save_bookmark stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sdk_save_bookmark": {
      "limits": [
        {
          "counter": "sdk_save_bookmark_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches UI Bridge MCP, so you can run agents against it safely.

FAQ

Questions about sdk_save_bookmark

What does the sdk_save_bookmark tool do? +

Save a snapshot bookmark for later diffing. Captures current UI state. 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.

How do I enforce a policy on sdk_save_bookmark? +

Register the UI Bridge MCP server in PolicyLayer and add a rule for sdk_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.

What risk level is sdk_save_bookmark? +

sdk_save_bookmark is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sdk_save_bookmark? +

Yes. Add a rate_limit block to the sdk_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.

How do I block sdk_save_bookmark completely? +

Set action: deny in the PolicyLayer policy for sdk_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.

What MCP server provides sdk_save_bookmark? +

sdk_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.