sandbox_start

SERVERRokha SOURCEhttps://rokha.ai/mcp/jsonrpc

High RISK CLASS

Category Execute

Parameters 21 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/ai-rokha-rokha/sandbox-start.md

WHAT IT DOES

What sandbox_start does on Rokha

AI agents invoke sandbox_start to trigger actions in Rokha. 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
`browser`	boolean	—	true = a browser-capable (chromium) sandbox — costs 3 runs instead of 1
`wallet_address`	string	Yes

Parameters from the server's own tool schema.

RISK

Why sandbox_start is rated High

Allocates and initiates a sandbox execution environment that enables arbitrary code execution through paired sandbox_exec tool.

From the tool's definition Start the user's session sandbox, isolated cloud shell, runs work inside it.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs sandbox_start safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Rokha, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sandbox_start, this is the rule to start with:

sandbox_start Rate-limited

sandbox_start 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_start": {
      "limits": [
        {
          "counter": "sandbox_start_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 Rokha, apply this rule, and every sandbox_start call is checked against it from then on.

FAQ

Questions about sandbox_start

What does the sandbox_start tool do? +

Start the user's session sandbox (isolated cloud shell — the safe place to test untrusted tools; sandbox_exec runs work inside it). SPENDS the daily run allowance: 1 run, or 3 with browser: true (a chromium-capable sandbox) — confirm with the user before calling unless they just asked for one. Idempotent: an already-running sandbox is returned (existing: true), never doubled. Needs wallet_address; anon works. 429 = today's allowance is spent (resets tomorrow; logging in raises it). It is categorised as a Execute tool in the Rokha MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does sandbox_start accept? +

sandbox_start accepts 2 parameters: browser, wallet_address. Required: wallet_address. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on sandbox_start? +

Register the Rokha MCP server in PolicyLayer and add a rule for sandbox_start: 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 Rokha. Nothing to install.

What risk level is sandbox_start? +

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

Can I rate-limit sandbox_start? +

Yes. Add a rate_limit block to the sandbox_start 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_start completely? +

Set action: deny in the PolicyLayer policy for sandbox_start. 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_start? +

sandbox_start is provided by the Rokha MCP server (https://rokha.ai/mcp/jsonrpc). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Rokha, and thousands of servers like it.

This server

All 216 Rokha tools → High-risk tools on this server →

Across the catalogue

start_devtools_monitoring on Percepta MCP Server →team_manager_start_room on Team Manager MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

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