Uploads a local file to the specified sandbox. Parameters: sandbox_id (string), local_file_path (string), dest_path (string, optional, default: /app/results).
AI agents use upload_file_to_sandbox to create or update resources in MCP Sandbox — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Sandbox environment.
This tool creates or modifies data within a sandbox by uploading files to a destination path. While it does not permanently destroy data or execute arbitrary code directly, it can introduce malicious payloads (scripts, binaries) that may be executed by other tools on the server (e.g., execute_python_code, execute_terminal_command).
From the tool's definition Tool description states it 'Uploads a local file to the specified sandbox' with parameters for source and destination paths, which creates new data in the sandbox environment.
Documented attack patterns abuse exactly the kind of access upload_file_to_sandbox gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Sandbox, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_file_to_sandbox:
{
"version": "1",
"default": "deny",
"tools": {
"upload_file_to_sandbox": {
"limits": [
{
"counter": "upload_file_to_sandbox_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}upload_file_to_sandbox stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Uploads a local file to the specified sandbox. Parameters: sandbox_id (string), local_file_path (string), dest_path (string, optional, default: /app/results). It is categorised as a Write tool in the MCP Sandbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Sandbox MCP server in PolicyLayer and add a rule for upload_file_to_sandbox: 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 Sandbox. Nothing to install.
upload_file_to_sandbox is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the upload_file_to_sandbox 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 upload_file_to_sandbox. 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.
upload_file_to_sandbox is provided by the MCP Sandbox MCP server (johanli233/mcp-sandbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Sandbox, 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.
7 MCP Sandbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.