Personal Agent Gateway: AUTHOR a new OAuth (engine 'api', authorization-code + PKCE) connector for one of YOUR credentialed services. Starts the one-time consent flow and returns an auth_url to open in a browser plus a connect_id. On the same machine a loopback callback completes automatically; o...
AI agents use gateway_connect to create or update resources in Yaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | Yes | Connector id (e.g. 'google') |
scopes | array | — | OAuth scopes to request |
authUrl | string | Yes | OAuth2 authorization endpoint |
surface | string | Yes | API base URL the capabilities call (e.g. 'https://www.googleapis.com') |
clientId | string | — | OAuth client id (public) |
tokenUrl | string | Yes | OAuth2 token endpoint |
capabilities | array | Yes | Read capabilities to expose. Each: {id, verb:'get', flow:{type:'api', method:'GET', path}, answerSchema} |
clientSecret | string | — | OAuth client secret for confidential clients — stored in your vault, never in the manifest. Omit for public PKCE clients. |
Parameters from the server's own tool schema.
An AI agent can call gateway_connect faster than any human can review — one bad instruction and it creates or modifies resources in Yaver by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Personal Agent Gateway: AUTHOR a new OAuth (engine 'api', authorization-code + PKCE) connector for one of YOUR credentialed services. Starts the one-time consent flow and returns an auth_url to open in a browser plus a connect_id. On the same machine a loopback callback completes automatically; otherwise call gateway_connect_finish with the pasted code. The client secret (if any) is stored ONLY in your vault, NEVER in the manifest. READ-ONLY: only GET capabilities may be authored. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
gateway_connect accepts 8 parameters: id, scopes, authUrl, surface, clientId, tokenUrl, capabilities, clientSecret. Required: id, authUrl, surface, tokenUrl, capabilities. 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_connect: 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_connect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gateway_connect 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_connect. 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_connect 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.