Use this when you want to perform a carrier operation but don't know which specific tool to call. Describe your intent in plain language and carrier_ask will identify the correct tool(s) and suggest the required parameters. For simple read intents, it executes directly and returns results. For de...
Part of the Carrier MCP: Give Your AI Agent Global Connectivity server.
Free to start. No card required.
AI agents call carrier_ask to retrieve information from Carrier MCP: Give Your AI Agent Global Connectivity without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though carrier_ask only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"carrier_ask": {}
}
}See the full Carrier MCP: Give Your AI Agent Global Connectivity policy for all 65 tools.
These attack patterns abuse exactly the kind of access carrier_ask gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Use this when you want to perform a carrier operation but don't know which specific tool to call. Describe your intent in plain language and carrier_ask will identify the correct tool(s) and suggest the required parameters. For simple read intents, it executes directly and returns results. For destructive operations it returns a confirm_token that you must pass in a second call. Params: intent (string — natural language description of what you want to do, e.g. 'throttle ICCID 8932... to 256kbps' or 'show me Mango fleet usage this week'), context (optional object with iccid, account_id, reseller_id if already known). Returns: RouteResult — one of: confirmed (read op executed), pending_confirm (destructive, returns confirm_token), ambiguous (clarifying question), none (no match). Do NOT use this as a substitute for calling tools directly when you know the right tool — direct tool calls are faster and cheaper. Use carrier_ask only for ambiguous or exploratory intents. STATUS: scaffold — routing engine not yet active (follow-up PR). Currently echoes intent back.. It is categorised as a Read tool in the Carrier MCP: Give Your AI Agent Global Connectivity MCP Server, which means it retrieves data without modifying state.
Register the Carrier MCP: Give Your AI Agent Global Connectivity MCP server in PolicyLayer and add a rule for carrier_ask: 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 Carrier MCP: Give Your AI Agent Global Connectivity. Nothing to install.
carrier_ask 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 carrier_ask 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 carrier_ask. 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.
carrier_ask is provided by the Carrier MCP: Give Your AI Agent Global Connectivity MCP server (carrier/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 65 Carrier MCP: Give Your AI Agent Global Connectivity tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.