Send an SMS to a mobile number using minus sign to separate international prefix from the number
AI agents invoke send_sms to trigger actions in Openapi Mcp Sdk. 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.
Sending an SMS triggers an external operation with real-world effects (a message is delivered to a real phone number). It cannot be trivially undone, may have cost implications, and could be misused for spam or social engineering. It falls under Execute as it triggers an external operation, with high severity due to the potential for abuse at scale.
From the tool's definition 'Send an SMS to a mobile number' — the tool actively sends a message to an external party
Documented attack patterns abuse exactly the kind of access send_sms gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openapi Mcp Sdk, and nothing reaches the server without passing your rules. This is the rule we recommend for send_sms:
{
"version": "1",
"default": "deny",
"tools": {
"send_sms": {
"limits": [
{
"counter": "send_sms_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}send_sms stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Send an SMS to a mobile number using minus sign to separate international prefix from the number. It is categorised as a Execute tool in the Openapi Mcp Sdk MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Openapi Mcp Sdk MCP server in PolicyLayer and add a rule for send_sms: 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 Openapi Mcp Sdk. Nothing to install.
send_sms 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 send_sms 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 send_sms. 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.
send_sms is provided by the Openapi Mcp Sdk MCP server (openapi/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openapi Mcp Sdk, 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.
41 Openapi Mcp Sdk tools catalogued and risk-classified — across an index of 43,000+ MCP servers.