Parses a natural-language command (e.g. 'renew my SLA #42 for 5 years', 'check reputation for 0x…', 'pay 1.50 USDC to 0x…') into a structured InsureLink action plan with endpoint, params, payment requirements, and confidence. Free preview returns the supported grammar; full classification require...
Part of the InsureLink server.
Free to start. No card required.
AI agents call voice_intent to retrieve information from InsureLink 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 voice_intent 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": {
"voice_intent": {}
}
}See the full InsureLink policy for all 28 tools.
These attack patterns abuse exactly the kind of access voice_intent 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.
Parses a natural-language command (e.g. 'renew my SLA #42 for 5 years', 'check reputation for 0x…', 'pay 1.50 USDC to 0x…') into a structured InsureLink action plan with endpoint, params, payment requirements, and confidence. Free preview returns the supported grammar; full classification requires x402 payment ($0.001) at the paid endpoint.. It is categorised as a Read tool in the InsureLink MCP Server, which means it retrieves data without modifying state.
Register the InsureLink MCP server in PolicyLayer and add a rule for voice_intent: 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 InsureLink. Nothing to install.
voice_intent 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 voice_intent 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 voice_intent. 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.
voice_intent is provided by the InsureLink MCP server (https://ivnmscuuljqubunqcgkh.supabase.co/functions/v1/mcp-server/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 28 InsureLink 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.