start_sandbox_execution

Start a new sandboxed execution for an Agent. Freezes the policy snapshot and returns the execution record + policy envelope.

SERVERTodo for AI MCP Server SOURCEtodo-for-ai/todo-for-ai-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/todo-for-ai-todo-for-ai-mcp/start-sandbox-execution.md

WHAT IT DOES

What start_sandbox_execution does on Todo for AI MCP Server

AI agents invoke start_sandbox_execution to trigger actions in Todo for AI MCP Server. 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.

RISK

Why start_sandbox_execution is rated High

start_sandbox_execution triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs start_sandbox_execution safely

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

start_sandbox_execution Rate-limited

start_sandbox_execution 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": {
    "start_sandbox_execution": {
      "limits": [
        {
          "counter": "start_sandbox_execution_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 Todo for AI MCP Server, apply this rule, and every start_sandbox_execution call is checked against it from then on.

FAQ

Questions about start_sandbox_execution

What does the start_sandbox_execution tool do? +

Start a new sandboxed execution for an Agent. Freezes the policy snapshot and returns the execution record + policy envelope. It is categorised as a Execute tool in the Todo for AI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_sandbox_execution? +

Register the Todo for AI MCP Server MCP server in PolicyLayer and add a rule for start_sandbox_execution: 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 Todo for AI MCP Server. Nothing to install.

What risk level is start_sandbox_execution? +

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

Can I rate-limit start_sandbox_execution? +

Yes. Add a rate_limit block to the start_sandbox_execution 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 start_sandbox_execution completely? +

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

start_sandbox_execution is provided by the Todo for AI MCP Server MCP server (todo-for-ai/todo-for-ai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Todo for AI MCP Server, and thousands of servers like it.

This server

All 244 Todo for AI MCP Server 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 →