runtime_control
Send a control action (tap/swipe/pinch/navigate/text/key) to a remote-runtime session — the seam a runner uses to browse the app, not just the code.
This record as markdown: /tools/io-github-kivanccakmak-yaver/runtime-control.md
What runtime_control does on Yaver
AI agents invoke runtime_control 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 |
|---|---|---|---|
x | integer | — | |
y | integer | — | |
x2 | integer | — | Swipe end-point x. |
y2 | integer | — | Swipe end-point y. |
key | string | — | |
url | string | — | Target URL for action=navigate. http/https only. For browser-window this is the ONLY way to show content — the window opens at about:blank. |
text | string | — | |
scale | number | — | Pinch scale centred on x,y: >1 zooms in (fingers apart), <1 zooms out. Only used by action=pinch|zoom. |
action | string | Yes | tap | swipe | pinch | zoom | navigate | text | key |
sessionId | string | Yes | |
durationMs | integer | — | Swipe or pinch duration in ms. |
Parameters from the server's own tool schema.
Why runtime_control is rated High
Executes UI interactions on a remote device session, enabling arbitrary app control.
From the tool's definition Send a control action (tap/swipe/pinch/navigate/text/key) to a remote-runtime session
Risk signalsAccepts URL/endpoint input (url) · High parameter count (11 properties)
Attacks that exploit this kind of access
The rule that runs runtime_control 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_control, this is the rule to start with:
runtime_control 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_control call is checked against it from then on.
Questions about runtime_control
Send a control action (tap/swipe/pinch/navigate/text/key) to a remote-runtime session — the seam a runner uses to browse the app, not just the code. 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_control accepts 11 parameters: x, y, x2, y2, key, url, text, scale, action, sessionId, durationMs. Required: action, 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_control: 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_control 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_control 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_control. 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_control 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