[Host] End active meeting. Locks history.
AI agents use end_meeting to create or update resources in N2n Nexus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your N2n Nexus environment.
This tool writes metadata about a meeting's status and access state rather than deleting data. The action is reversible in principle (an admin could reopen or unlock), making it Write rather than Destructive. The 'locks history' phrase indicates state modification, not data deletion.
From the tool's definition Tool description states 'End active meeting. Locks history.' — this modifies meeting state by concluding an active session and applying a lock to the history, which is a reversible state change (the meeting record persists, but is marked as ended/locked).
Documented attack patterns abuse exactly the kind of access end_meeting gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and N2n Nexus, and nothing reaches the server without passing your rules. This is the rule we recommend for end_meeting:
{
"version": "1",
"default": "deny",
"tools": {
"end_meeting": {
"limits": [
{
"counter": "end_meeting_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}end_meeting stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
[Host] End active meeting. Locks history. It is categorised as a Write tool in the N2n Nexus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the N2n Nexus MCP server in PolicyLayer and add a rule for end_meeting: 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 N2n Nexus. Nothing to install.
end_meeting 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 end_meeting 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 end_meeting. 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.
end_meeting is provided by the N2n Nexus MCP server (n2ns/n2n-nexus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from N2n Nexus, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
22 N2n Nexus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.