AI agents call get-session-events 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.
This tool retrieves and queries historical event data from a workflow instance. It has no side effects—it does not modify, create, or delete any data. The sibling tools like 'log-event-to-bus', 'handle-latest-event', and 'complete-slice' are the ones that would mutate state; this tool only exposes existing structured data for inspection, typical of Read operations.
From the tool's definition Tool returns a read-only view of event history: 'Return the full structured event list for a workflow instance'. The description indicates data retrieval ('Used by UIs that render a timeline') with no modification, creation, or deletion of data.
Attacks that exploit this kind of access
Return the full structured event list for a workflow instance (oldest first). Used by UIs that render a timeline. 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 get-session-events: 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.
get-session-events 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 get-session-events 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 get-session-events. 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.
get-session-events 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 →