AI agents invoke hangup_voice to trigger actions in Seven. 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.
Hanging up a voice call triggers an external operation (terminating an active call on the telephony network). It is not purely destructive data deletion, but it executes an irreversible real-world action (the call ends and cannot be resumed). This falls under Execute as it triggers an external operation with immediate, permanent effects on an active communication session.
From the tool's definition 'End an active voice call' — terminates an ongoing external telephony operation
Attacks that exploit this kind of access
End an active voice call. It is categorised as a Execute tool in the Seven MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Seven MCP server in PolicyLayer and add a rule for hangup_voice: 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 Seven. Nothing to install.
hangup_voice 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 hangup_voice 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 hangup_voice. 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.
hangup_voice is provided by the Seven MCP server (seven-io/seven-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 →