check_sandbox_command
Check if a command is allowed by a local sandbox profile (dry-run explain).
This record as markdown: /tools/todos/check-sandbox-command.md
What check_sandbox_command does on Todos
AI agents call check_sandbox_command to retrieve information from Todos without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why check_sandbox_command is rated Low
This is a read-only operation that validates or inspects sandbox rules without executing anything or changing data. The 'dry-run' and 'check' language indicates it merely retrieves information about policy compliance. The lack of execution, modification, or deletion semantics places it firmly in the Read category with low severity.
From the tool's definition The tool performs a dry-run check/explain operation ('dry-run explain') against a sandbox profile, with no indication of executing commands, modifying state, or causing side effects. It queries whether a command would be allowed.
Attacks that exploit this kind of access
The rule that runs check_sandbox_command safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Todos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For check_sandbox_command, this is the rule to start with:
check_sandbox_command is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Todos, apply this rule, and every check_sandbox_command call is checked against it from then on.
Questions about check_sandbox_command
Check if a command is allowed by a local sandbox profile (dry-run explain). It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for check_sandbox_command: 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 Todos. Nothing to install.
check_sandbox_command is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_sandbox_command 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 check_sandbox_command. 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.
check_sandbox_command is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Todos, and thousands of servers like it.
This server
Across the catalogue