AI agents call events-dump to retrieve information from Mmc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The events-dump tool retrieves and displays historical event log data without modifying, deleting, or executing any operations. It is purely informational for reviewing past events in a session. The warning about user request/skill-defined tool call is a usage restriction, not a functional capability that changes its read-only nature. No data is created, modified, deleted, or executed — only queried and displayed.
From the tool's definition Tool description states it 'Displays a formatted, paginated dump of the event log' and 'Use to review recorded events in the session' — these are read-only retrieval operations with no side effects.
Attacks that exploit this kind of access
ONLY USE AT USER REQUEST OR SKILL DEFINED TOOL CALL!!! Displays a formatted, paginated dump of the event log. Use to review recorded events in the session. It is categorised as a Read tool in the Mmc MCP Server, which means it retrieves data without modifying state.
Register the Mmc MCP server in PolicyLayer and add a rule for events-dump: 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.
events-dump 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 events-dump 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 events-dump. 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.
events-dump 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 →