gateway_intent · Yaver MCP: Risk & Policy

WHAT IT DOES

What gateway_intent does on Yaver

AI agents invoke gateway_intent to trigger actions in Yaver. 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.

PARAMETERS

Parameter	Type	Required	Description
`utterance`	string	Yes	What the user said (e.g. 'top up my transit card by 100')

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why gateway_intent needs a policy

gateway_intent triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gateway_intent Rate-limited

gateway_intent 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "gateway_intent": {
      "limits": [
        {
          "counter": "gateway_intent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Yaver, so you can run agents against it safely.

FAQ

Questions about gateway_intent

What does the gateway_intent tool do? +

Personal Agent Gateway: route a natural-language utterance to the right engine — a coding task (runner), a gateway READ (runs it, returns the answer), or a gateway ACT (returns a dry-run preview + act_id, never auto-executes). This is the single entry point a voice/watch surface uses so the user need not name a connector. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does gateway_intent accept? +

gateway_intent accepts 1 parameter: utterance. Required: utterance. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on gateway_intent? +

Register the Yaver MCP server in PolicyLayer and add a rule for gateway_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 Yaver. Nothing to install.

What risk level is gateway_intent? +

gateway_intent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit gateway_intent? +

Yes. Add a rate_limit block to the gateway_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.

How do I block gateway_intent completely? +

Set action: deny in the PolicyLayer policy for gateway_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.

What MCP server provides gateway_intent? +

gateway_intent is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.