Create a new call
AI agents invoke create_call to trigger actions in VoIPBin MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Creating a call triggers an external telephony action (dialing a real phone number), which is an Execute-level operation. It cannot be considered a simple Write because it causes real-world effects beyond data storage. Severity is high because misuse could result in unwanted calls to arbitrary recipients, potential harassment, and financial implications from call charges.
From the tool's definition 'Create a new call' — initiates an outbound VoIP call, which is an external real-world operation with side effects (phone call placed, potentially billed, recipient is contacted).
Attacks that exploit this kind of access
Create a new call. It is categorised as a Execute tool in the VoIPBin MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the VoIPBin MCP Server MCP server in PolicyLayer and add a rule for create_call: 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.
create_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_call 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 create_call. 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.
create_call 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 →