Get the status of active voice calls
AI agents call get_call_status to retrieve information from Voice Assistant 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 call status information without side effects. It neither initiates calls, modifies call state, executes commands, deletes data, nor involves financial transactions. The read-only nature and lack of side effects place it clearly in the Read category with low severity, as an agent misusing this tool could at worst access metadata about calls but cannot cause operational damage.
From the tool's definition Tool name 'get_call_status' and description 'Get the status of active voice calls' indicate a query-only operation that retrieves information about existing calls without modification or execution of new actions.
Attacks that exploit this kind of access
Get the status of active voice calls. It is categorised as a Read tool in the Voice Assistant MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Voice Assistant MCP Server MCP server in PolicyLayer and add a rule for get_call_status: 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 Voice Assistant MCP Server. Nothing to install.
get_call_status 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_call_status 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_call_status. 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_call_status is provided by the Voice Assistant MCP Server MCP server (prakharbhardwaj/voice-agent-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 →