sanitize_document
AI agents use sanitize_document 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.
Based on the server context (PII sanitisation using Microsoft Presidio) and the sibling tool 'sanitize_text', 'sanitize_document' most likely modifies a document by detecting and replacing/redacting PII, which is a Write operation (reversible transformation of data). However, the empty description significantly lowers confidence.
From the tool's definition Tool name 'sanitize_document' on a PII detection/sanitisation server; description is empty and uninformative.
Attacks that exploit this kind of access
sanitize_document. 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.
Register the Mcp Pii Guard Au MCP server in PolicyLayer and add a rule for sanitize_document: 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.
sanitize_document 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 sanitize_document 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 sanitize_document. 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.
sanitize_document 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →