Read, write, list, or delete files in a sandbox session.
AI agents call sandbox_file_ops to permanently remove resources in MCP Multi-Language Sandbox — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While this tool includes read (Read category) and write (Write category) capabilities, the destructive capability—deleting files—takes precedence under the severity hierarchy. File deletion is irreversible and represents the most severe operation the tool can perform. In a sandbox context with persistent sessions, deleted files cannot be recovered.
From the tool's definition Tool description explicitly states it can 'delete files in a sandbox session.' The ability to irreversibly remove files qualifies as destructive, even though the tool also supports read and write operations.
Attacks that exploit this kind of access
Read, write, list, or delete files in a sandbox session. It is categorised as a Destructive tool in the MCP Multi-Language Sandbox MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Multi-Language Sandbox MCP server in PolicyLayer and add a rule for sandbox_file_ops: 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 MCP Multi-Language Sandbox. Nothing to install.
sandbox_file_ops is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the sandbox_file_ops 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_file_ops. 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_file_ops is provided by the MCP Multi-Language Sandbox MCP server (pit-cl/mcp-multilang-sandbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →