AI agents use send_voice to create or update resources in Amadeus-QQ-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Amadeus-QQ-MCP environment.
Based on the server context (QQ messaging platform) and naming convention consistent with sibling tools like send_message and send_image, send_voice likely sends a voice/audio message to a user or group. This is a Write operation as it creates and delivers content. Severity is high because it can send audio content to individuals or groups without their explicit consent, with potential for misuse.
From the tool's definition Tool name 'send_voice' on a QQ messaging server that supports send_message and send_image sibling tools
Documented attack patterns abuse exactly the kind of access send_voice gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Amadeus-QQ-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for send_voice:
{
"version": "1",
"default": "deny",
"tools": {
"send_voice": {
"limits": [
{
"counter": "send_voice_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_voice 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.
send_voice. It is categorised as a Write tool in the Amadeus-QQ-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Amadeus-QQ- MCP server in PolicyLayer and add a rule for send_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 Amadeus-QQ-MCP. Nothing to install.
send_voice 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 send_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 send_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.
send_voice is provided by the Amadeus-QQ- MCP server (julesliu390/amadeus-qq-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Amadeus-QQ-MCP, 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.
10 Amadeus-QQ-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.