sandbox_run

SERVERYaver SOURCEyaver-cli

High RISK CLASS

Category Execute

Parameters 72 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-kivanccakmak-yaver/sandbox-run.md

WHAT IT DOES

What sandbox_run does on Yaver

AI agents invoke sandbox_run 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
`files`	array	Yes	Phone sandbox files as {path, content}. Paths are posix-relative and may not escape the project root.
`prompt`	string	Yes	Requested change to make in the sandbox source tree.
`runner`	string	—	Only opencode is currently supported.
`schema`	object	—	Optional phone-project backend schema context.
`device_id`	string	—	Optional owned Yaver device id/name/alias to run OpenCode/GLM on. Empty = this machine.
`framework`	string	—	Framework label for prompting, default React Native (Expo).
`timeoutMs`	integer	—	Runner timeout in milliseconds, default 180000, max 600000.

Parameters from the server's own tool schema.

RISK

Why sandbox_run is rated High

This tool executes code compilation and build operations (OpenCode) on local or remote devices, with effects that depend on the source tree content and GLM model decisions. While it returns a diff rather than deploying directly, it triggers external operations (compilation, execution on remote devices) whose outcomes depend on untrusted input (LLM-generated EditPlans).

From the tool's definition 'run the Mobile Sandbox edit loop', 'runs OpenCode with GLM', 'ships a phone-style React Native / Expo source tree to this machine or an owned remote Yaver device'

Risk signalsAccepts file system path (files[].path) · Accepts raw HTML/template content (files[].content)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs sandbox_run 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 sandbox_run, this is the rule to start with:

sandbox_run Rate-limited

sandbox_run 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sandbox_run": {
      "limits": [
        {
          "counter": "sandbox_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every sandbox_run call is checked against it from then on.

FAQ

Questions about sandbox_run

What does the sandbox_run tool do? +

Run the Mobile Sandbox edit loop from a headless MCP client. Ships a phone-style React Native / Expo source tree to this machine or an owned remote Yaver device, runs OpenCode with GLM there, and returns an EditPlan-shaped diff. The GLM key stays on the machine that runs the tool; configure it with runner_auth_set/runner_auth_setup or ZAI_API_KEY/GLM_API_KEY. 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.

What parameters does sandbox_run accept? +

sandbox_run accepts 7 parameters: files, prompt, runner, schema, device_id, framework, timeoutMs. Required: files, prompt. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on sandbox_run? +

Register the Yaver MCP server in PolicyLayer and add a rule for sandbox_run: 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.

What risk level is sandbox_run? +

sandbox_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit sandbox_run? +

Yes. Add a rate_limit block to the sandbox_run 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.

How do I block sandbox_run completely? +

Set action: deny in the PolicyLayer policy for sandbox_run. 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.

What MCP server provides sandbox_run? +

sandbox_run 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.

KEEP EXPLORING

More on Yaver, and thousands of servers like it.

This server

All 645 Yaver tools → High-risk tools on this server →

Across the catalogue

shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →