AI agents use guest_config 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 |
|---|---|---|---|
email | string | — | Guest email to view/update (omit to list all) |
usage_mode | string | — | When guest can use: always, idle-only, scheduled |
daily_limit | integer | — | Max task-seconds per day (0 = unlimited) |
ram_limit_mb | integer | — | RAM cap in MB for the guest on this host |
priority_mode | string | — | Scheduling policy for guest tasks |
allowed_runners | array | — | Runner IDs the guest can use (empty = all) |
resource_preset | string | — | Share preset: machine-only, machine-with-host-keys, desktop-control, desktop-control-with-host-keys |
cpu_limit_percent | integer | — | Soft CPU share cap for the guest on this host (1-100) |
require_isolation | boolean | — | Require this guest's tasks to run in Docker isolation when available |
use_host_api_keys | boolean | — | Let the guest consume host-managed API keys without revealing the raw key |
allow_guest_api_keys | boolean | — | Allow the guest to bring and use their own API keys on the shared infra |
allow_tunnel_forward | boolean | — | Allow guest access to host-approved local tunnel forwards |
Parameters from the server's own tool schema.
An AI agent can call guest_config 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.
Risk signalsHigh parameter count (14 properties)
Attacks that exploit this kind of access
View or update guest config (limits, runners, share preset, resource controls). Without email: list all. With email: show/update config. 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.
guest_config accepts 12 parameters: email, usage_mode, daily_limit, ram_limit_mb, priority_mode, allowed_runners, resource_preset, cpu_limit_percent, require_isolation, use_host_api_keys, allow_guest_api_keys, allow_tunnel_forward. 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 guest_config: 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.
guest_config 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 guest_config 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 guest_config. 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.
guest_config 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.