Retrieve a list of call recordings
AI agents call get_recordings to retrieve information from VoIPBin MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries call recording data with no capability to create, modify, delete, or execute operations. It falls squarely within the Read category. While call recordings may contain sensitive audio content, the tool itself performs only data retrieval.
From the tool's definition Tool name 'get_recordings' and description 'Retrieve a list of call recordings' indicate a read-only operation that fetches existing data without modification or side effects.
Attacks that exploit this kind of access
Retrieve a list of call recordings. It is categorised as a Read tool in the VoIPBin MCP Server MCP Server, which means it retrieves data without modifying state.
Register the VoIPBin MCP Server MCP server in PolicyLayer and add a rule for get_recordings: 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 VoIPBin MCP Server. Nothing to install.
get_recordings 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_recordings 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_recordings. 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_recordings is provided by the VoIPBin MCP Server MCP server (nrjchnd/voipbin-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 →