Build a self-contained native binary (xcodebuild Release / gradle installRelease) and install it on a WIFI-paired phone via the agent's host machine. Same long-running build pipeline as wire_push, but routes through the wireless device picker. If no paired wireless device is found, the error incl...
AI agents use wireless_push 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 |
|---|---|---|---|
path | string | — | Project path. Empty = the AI session's working directory (the dir Claude Code / Codex / opencode was started in) — typically what you want when iterating inside |
config | string | — | Build configuration. Default Release. |
device | string | — | Specific device UDID (iOS) or wireless serial like '192.168.1.42:5555' (Android). Empty = first paired wireless device for the platform. Run wireless_detect fir |
platform | string | — | Force a platform when the project supports both. Empty = auto-pick. |
no_launch | boolean | — | Install but don't launch. Default false. |
timeout_sec | integer | — | Hard timeout in seconds. Default 1800 (30 min). |
Parameters from the server's own tool schema.
An AI agent can call wireless_push 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 signalsAccepts file system path (path)
Attacks that exploit this kind of access
Build a self-contained native binary (xcodebuild Release / gradle installRelease) and install it on a WIFI-paired phone via the agent's host machine. Same long-running build pipeline as wire_push, but routes through the wireless device picker. If no paired wireless device is found, the error includes a count of visible-unpaired devices so you can chain wireless_setup_android. Returns {ok, exit_code, device, platform, transport, stack, log_path, log_tail, elapsed_sec}. 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.
wireless_push accepts 6 parameters: path, config, device, platform, no_launch, timeout_sec. 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 wireless_push: 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.
wireless_push 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 wireless_push 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 wireless_push. 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.
wireless_push 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.