Personal Agent Gateway: read state from one of YOUR credentialed apps/services (your wired connectors) as a structured answer. READ-ONLY — no writes/actions. Credentials live in your vault; nothing is sent to Convex. Use the connector + capability ids from your connector registry.
AI agents call gateway_query to retrieve information from Yaver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
params | object | — | Optional string params substituted into the capability flow ({key} placeholders) |
connector | string | Yes | Connector id (e.g. 'google') |
capability | string | Yes | Read capability id on that connector (e.g. 'next_event') |
Parameters from the server's own tool schema.
Even though gateway_query only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Personal Agent Gateway: read state from one of YOUR credentialed apps/services (your wired connectors) as a structured answer. READ-ONLY — no writes/actions. Credentials live in your vault; nothing is sent to Convex. Use the connector + capability ids from your connector registry. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
gateway_query accepts 3 parameters: params, 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_query: 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_query 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 gateway_query 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_query. 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_query 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.