write_workspace_file · Code Execution MCP: Risk & Policy

WHAT IT DOES

What write_workspace_file does on Code Execution MCP

AI agents use write_workspace_file to create or update resources in Code Execution MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Execution MCP environment.

WHY IT NEEDS A POLICY

Why write_workspace_file needs a policy

This tool creates or modifies files within a sandbox, which is a reversible action (files can be edited or deleted later). It does not execute code, delete data irreversibly, or move money. The sandbox constraint mitigates severity from 'high' to 'medium'—an agent could still write malicious scripts or corrupt workspace state, but the isolation prevents system-wide damage.

From the tool's definition Tool name 'write_workspace_file' and description 'Write a file to the sandbox workspace' indicate file creation/modification operations. The sandboxed context limits blast radius compared to unrestricted filesystem access.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

write_workspace_file Rate-limited

write_workspace_file 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "write_workspace_file": {
      "limits": [
        {
          "counter": "write_workspace_file_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Code Execution MCP, so you can run agents against it safely.

FAQ

Questions about write_workspace_file

What does the write_workspace_file tool do? +

Write a file to the sandbox workspace. It is categorised as a Write tool in the Code Execution MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on write_workspace_file? +

Register the Code Execution MCP server in PolicyLayer and add a rule for write_workspace_file: 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 Code Execution MCP. Nothing to install.

What risk level is write_workspace_file? +

write_workspace_file is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit write_workspace_file? +

Yes. Add a rate_limit block to the write_workspace_file 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.

How do I block write_workspace_file completely? +

Set action: deny in the PolicyLayer policy for write_workspace_file. 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.

What MCP server provides write_workspace_file? +

write_workspace_file is provided by the Code Execution MCP server (marc-shade/code-execution-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.