Dispatcher skill. Invoke this after receiving any non-null event from get-next-event, passing the event as context. • Interface event (has a matching skill with triggers_on_event): route to and execute that slice using complete-slice. • Automation / background event (no matching interface skill —...
AI agents invoke handle-latest-event to trigger actions in Mmc. 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.
This tool acts as a workflow dispatcher that routes and executes process steps, triggers other tools (complete-slice, get-next-event), and drives automated business process execution. It orchestrates multi-step workflows whose effects depend on the events being processed, making Execute the most appropriate category.
From the tool's definition Dispatcher skill... route to and execute that slice using complete-slice... immediately call get-next-event to continue
Attacks that exploit this kind of access
Dispatcher skill. Invoke this after receiving any non-null event from get-next-event, passing the event as context. • Interface event (has a matching skill with triggers_on_event): route to and execute that slice using complete-slice. • Automation / background event (no matching interface skill — the server handled it automatically): acknowledge the completed step, report it briefly to the user, then immediately call get-next-event to continue. • unexpected_last_event: the workflow has completed — summarise what happened and stop polling. It is categorised as a Execute tool in the Mmc MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mmc MCP server in PolicyLayer and add a rule for handle-latest-event: 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 Mmc. Nothing to install.
handle-latest-event 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 handle-latest-event 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 handle-latest-event. 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.
handle-latest-event is provided by the Mmc MCP server (modelmycontext/mmc-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 →