Place outbound phone calls to the granted audience using Vapi for telephony, ElevenLabs voice, and Claude Sonnet for the real-time conversation. Each call uses the system_prompt as the assistant's instructions; greeting is the first thing the recipient hears. Voicemail-drop on no-answer; live-tra...
Risk signalsHigh parameter count (10 properties)
Part of the Computeback server.
Free to start. No card required.
AI agents may call dispatch_voice_campaign to permanently remove or destroy resources in Computeback. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call dispatch_voice_campaign in a loop, permanently destroying resources in Computeback. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
{
"version": "1",
"default": "deny",
"hide": [
"dispatch_voice_campaign"
]
}See the full Computeback policy for all 28 tools.
These attack patterns abuse exactly the kind of access dispatch_voice_campaign gives an agent. Each links to the full case and the policy that stops it:
Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Place outbound phone calls to the granted audience using Vapi for telephony, ElevenLabs voice, and Claude Sonnet for the real-time conversation. Each call uses the system_prompt as the assistant's instructions; greeting is the first thing the recipient hears. Voicemail-drop on no-answer; live-transfer to a designated number when the lead matches the transfer trigger. TCPA-compliant (DNC list scrub + recipient-timezone 8am-9pm window). Outcomes flow back via the Vapi webhook → outcome event stream.. It is categorised as a Destructive tool in the Computeback MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Computeback MCP server in PolicyLayer and add a rule for dispatch_voice_campaign: 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 Computeback. Nothing to install.
dispatch_voice_campaign is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the dispatch_voice_campaign 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 dispatch_voice_campaign. 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.
dispatch_voice_campaign is provided by the Computeback MCP server (@autonomad1/computeback-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 28 Computeback tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.