Upload files to the Daytona workspace from text or base64-encoded binary content. Creates necessary parent directories automatically and verifies successful writes. Files persist during the session and have appropriate permissions for further tool operations. Supports overwrite controls and maint...
AI agents use file_upload to create or update resources in Daytona MCP Python Interpreter — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Daytona MCP Python Interpreter environment.
This tool creates or modifies files within a workspace environment. While uploads are reversible (files can be deleted or replaced), the high severity reflects that malicious file uploads could introduce malicious code, scripts, or data into the workspace, which sibling tools like shell_exec or python execution could then leverage for harmful purposes.
From the tool's definition Tool description states: 'Upload files to the Daytona workspace from text or base64-encoded binary content' and 'Creates necessary parent directories automatically.' The 'overwrite controls' language indicates reversible modification of files within the…
Documented attack patterns abuse exactly the kind of access file_upload gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Daytona MCP Python Interpreter, and nothing reaches the server without passing your rules. This is the rule we recommend for file_upload:
{
"version": "1",
"default": "deny",
"tools": {
"file_upload": {
"limits": [
{
"counter": "file_upload_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}file_upload 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.
Upload files to the Daytona workspace from text or base64-encoded binary content. Creates necessary parent directories automatically and verifies successful writes. Files persist during the session and have appropriate permissions for further tool operations. Supports overwrite controls and maintains original file formats. It is categorised as a Write tool in the Daytona MCP Python Interpreter MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Daytona MCP Python Interpreter MCP server in PolicyLayer and add a rule for file_upload: 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 Daytona MCP Python Interpreter. Nothing to install.
file_upload 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 file_upload 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 file_upload. 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.
file_upload is provided by the Daytona MCP Python Interpreter MCP server (nibzard/daytona-mcp-interpreter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Daytona MCP Python Interpreter, 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.
5 Daytona MCP Python Interpreter tools catalogued and risk-classified — across an index of 43,000+ MCP servers.