AI agents call get_conversation_users to retrieve information from Carbon Voice without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about users participating in a conversation. It has no side effects, does not modify data, execute code, delete anything, or commit financial transactions. It is a straightforward query operation that falls squarely into the Read category with low severity.
From the tool's definition Tool name 'get_conversation_users' and description 'Get users in a conversation' indicate a retrieval operation with no modification or execution of actions.
Documented attack patterns abuse exactly the kind of access get_conversation_users gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Carbon Voice, and nothing reaches the server without passing your rules. This is the rule we recommend for get_conversation_users:
{
"version": "1",
"default": "deny",
"tools": {
"get_conversation_users": {}
}
} get_conversation_users is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get users in a conversation. It is categorised as a Read tool in the Carbon Voice MCP Server, which means it retrieves data without modifying state.
Register the Carbon Voice MCP server in PolicyLayer and add a rule for get_conversation_users: 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 Carbon Voice. Nothing to install.
get_conversation_users 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_conversation_users 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_conversation_users. 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_conversation_users is provided by the Carbon Voice MCP server (phononx/cv-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Carbon Voice, 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.
28 Carbon Voice tools catalogued and risk-classified — across an index of 43,000+ MCP servers.