runtime_command
Run a session-level command (boot re-attach, project rerender/relaunch, launch-app, launch-feedback). The compatibility command run-guest rebuilds and relaunches the selected RN/Expo project app into the active simulator/emulator stream, including tvOS when available; launch-app requires bundleId...
This record as markdown: /tools/io-github-kivanccakmak-yaver/runtime-command.md
What runtime_command does on Yaver
AI agents invoke runtime_command 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 |
|---|---|---|---|
source | string | — | Optional trigger source label (e.g. shake, tap-menu). |
command | string | Yes | boot | run-guest | launch-app | launch-feedback |
workDir | string | — | Project root for run-guest when the session does not already carry workDir. |
bundleId | string | — | iOS/Android app bundle id for launch-app. |
sessionId | string | Yes |
Parameters from the server's own tool schema.
Why runtime_command is rated High
Executes arbitrary commands affecting project state, app builds, and simulator/emulator operations with significant blast radius.
From the tool's definition Run session-level command, rebuilds and relaunches project app, boot idempotent
Attacks that exploit this kind of access
The rule that runs runtime_command safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For runtime_command, this is the rule to start with:
runtime_command 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every runtime_command call is checked against it from then on.
Questions about runtime_command
Run a session-level command (boot re-attach, project rerender/relaunch, launch-app, launch-feedback). The compatibility command run-guest rebuilds and relaunches the selected RN/Expo project app into the active simulator/emulator stream, including tvOS when available; launch-app requires bundleId; boot is idempotent. 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.
runtime_command accepts 5 parameters: source, command, workDir, bundleId, sessionId. Required: command, sessionId. 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 runtime_command: 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.
runtime_command 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 runtime_command 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 runtime_command. 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.
runtime_command 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.
More on Yaver, and thousands of servers like it.
Across the catalogue