AI agents call get_user_voicemails to retrieve information from Oitvoip without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation that retrieves voicemail data. While classified as Read (no side effects), severity is elevated to medium because voicemails often contain sensitive personal or business communications. Unauthorized access could enable eavesdropping or privacy violations, even though the tool itself performs no destructive or system-level operations.
From the tool's definition Tool is named 'get_user_voicemails' and described as 'Get voicemails for a user' — a retrieval operation with no modification or deletion.
Attacks that exploit this kind of access
Get voicemails for a user. It is categorised as a Read tool in the Oitvoip MCP Server, which means it retrieves data without modifying state.
Register the Oitvoip MCP server in PolicyLayer and add a rule for get_user_voicemails: 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 Oitvoip. Nothing to install.
get_user_voicemails 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_user_voicemails 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_user_voicemails. 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_user_voicemails is provided by the Oitvoip MCP server (oitapps/oitvoip-mcp-server). 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 →