restore_pii · Code Execution MCP: Risk & Policy

WHAT IT DOES

What restore_pii does on Code Execution MCP

AI agents use restore_pii 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 restore_pii needs a policy

This tool reverses PII tokenization, mapping anonymized tokens back to real personal data (names, emails, SSNs, etc.). It modifies the state of data by de-anonymizing it, which is a Write operation. The severity is high because misuse could expose sensitive personal information — an AI agent calling this inappropriately could leak PII that was intentionally protected, representing a significant privacy risk.

From the tool's definition Restore tokenized PII back to original values

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

restore_pii Rate-limited

restore_pii 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": {
    "restore_pii": {
      "limits": [
        {
          "counter": "restore_pii_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 restore_pii

What does the restore_pii tool do? +

Restore tokenized PII back to original values. 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 restore_pii? +

Register the Code Execution MCP server in PolicyLayer and add a rule for restore_pii: 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 restore_pii? +

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

Can I rate-limit restore_pii? +

Yes. Add a rate_limit block to the restore_pii 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 restore_pii completely? +

Set action: deny in the PolicyLayer policy for restore_pii. 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 restore_pii? +

restore_pii 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.