Categorize the last computed diff. Returns category
AI agents call sdk_categorize_last_diff 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.
This tool retrieves and categorizes metadata about a diff that has already been computed. It performs analysis and returns results without modifying data, executing code, or triggering external operations. The operation is informational and has no side effects.
From the tool's definition Tool name and description indicate it categorizes and returns information about a previously computed diff: 'Categorize the last computed diff. Returns category'.
Attacks that exploit this kind of access
Categorize the last computed diff. Returns category. 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_categorize_last_diff: 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_categorize_last_diff 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_categorize_last_diff 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_categorize_last_diff. 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_categorize_last_diff 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 →