sanitize_text · Mcp Pii Guard Au MCP: Risk & Policy

WHAT IT DOES

What sanitize_text does on Mcp Pii Guard Au

AI agents use sanitize_text to create or update resources in Mcp Pii Guard Au — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Pii Guard Au environment.

WHY IT NEEDS A POLICY

Why sanitize_text needs a policy

Sanitization implies modifying or transforming text by redacting, masking, or replacing PII — a reversible or irreversible write operation on data. The description is empty, which lowers confidence. Given the server context (PII sanitisation for AI agents with tokenization/detokenization siblings), this tool most likely transforms input text by replacing PII with tokens or redacted placeholders (a Write operation).

From the tool's definition Tool name 'sanitize_text' on a server described as providing 'PII detection and sanitisation'; sibling tools include 'sanitize_document' and 'detokenize_text'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sanitize_text Rate-limited

sanitize_text 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": {
    "sanitize_text": {
      "limits": [
        {
          "counter": "sanitize_text_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 Mcp Pii Guard Au, so you can run agents against it safely.

FAQ

Questions about sanitize_text

What does the sanitize_text tool do? +

sanitize_text. It is categorised as a Write tool in the Mcp Pii Guard Au MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sanitize_text? +

Register the Mcp Pii Guard Au MCP server in PolicyLayer and add a rule for sanitize_text: 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 Pii Guard Au. Nothing to install.

What risk level is sanitize_text? +

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

Can I rate-limit sanitize_text? +

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

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

sanitize_text is provided by the Mcp Pii Guard Au MCP server (mattwagstaff/mcp-pii-guard-au). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.