Disable change buffering in the runner
AI agents use ui_change_buffer_disable 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.
This tool changes the state of a system feature (change buffering) by disabling it. This is a reversible configuration change (buffering can be re-enabled), so it falls under Write rather than Destructive. However, disabling buffering could affect UI change tracking reliability, giving it medium severity if misused.
From the tool's definition 'Disable change buffering in the runner' — modifies a configuration/operational setting in the runner
Attacks that exploit this kind of access
Disable change buffering 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_change_buffer_disable: 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_change_buffer_disable 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_change_buffer_disable 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_change_buffer_disable. 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_change_buffer_disable 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 →