Read a file from the sandbox filesystem and return its contents as text.
AI agents call sandbox_fs_read to retrieve information from Microsandbox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file contents from a sandboxed filesystem without creating, modifying, or deleting data. It is a pure read operation with no side effects. The sandboxed context further limits potential impact compared to reading from a host system. Severity is low because reading files, even within a sandbox, poses minimal direct risk unless the sandbox contains highly sensitive information.
From the tool's definition Tool name is 'sandbox_fs_read' and description states it will 'Read a file from the sandbox filesystem and return its contents as text.' The verb 'read' and return of file contents indicate data retrieval with no modification.
Documented attack patterns abuse exactly the kind of access sandbox_fs_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Microsandbox, and nothing reaches the server without passing your rules. This is the rule we recommend for sandbox_fs_read:
{
"version": "1",
"default": "deny",
"tools": {
"sandbox_fs_read": {}
}
}sandbox_fs_read is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read a file from the sandbox filesystem and return its contents as text. It is categorised as a Read tool in the Microsandbox MCP Server, which means it retrieves data without modifying state.
Register the Microsandbox MCP server in PolicyLayer and add a rule for sandbox_fs_read: 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 Microsandbox. Nothing to install.
sandbox_fs_read 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 sandbox_fs_read 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 sandbox_fs_read. 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.
sandbox_fs_read is provided by the Microsandbox MCP server (superradcompany/microsandbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Microsandbox, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 Microsandbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.