Personal Agent Gateway: perform an ACTION (write) as you on one of YOUR connectors — start a charge, buy a ticket, place an order, pay. By DEFAULT (execute omitted/false) this is a DRY-RUN: it returns a preview (method+endpoint or app steps) + the Policy Guard verdict + an act_id, and changes NOT...
AI agents invoke gateway_act 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
params | object | — | String params substituted into the act flow ({key} placeholders). 'confirm':'yes' inline-confirms a low-risk act; '__jurisdiction' sets the Policy Guard region. |
execute | boolean | — | false/omitted = dry-run (default, safe). true = run the pipeline now. |
connector | string | Yes | Connector id |
capability | string | Yes | Act capability id (a write verb on that connector) |
Parameters from the server's own tool schema.
gateway_act 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
Personal Agent Gateway: perform an ACTION (write) as you on one of YOUR connectors — start a charge, buy a ticket, place an order, pay. By DEFAULT (execute omitted/false) this is a DRY-RUN: it returns a preview (method+endpoint or app steps) + the Policy Guard verdict + an act_id, and changes NOTHING. To run it, either set execute:true (low-risk acts may confirm inline via params.confirm='yes'; high/financial acts still require a tapped approval on your phone), or call gateway_act_confirm with the act_id. Credentials live in your vault; the act is recorded in a local audit ledger (never Convex). 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.
gateway_act accepts 4 parameters: params, execute, connector, capability. Required: connector, capability. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for gateway_act: 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.
gateway_act 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 gateway_act 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 gateway_act. 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.
gateway_act 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.