detokenize_text
AI agents call detokenize_text to retrieve information from Mcp Pii Guard Au without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the context of a PII detection/sanitization server, detokenize_text likely reconstructs or analyzes tokenized text (a read operation). The lack of description creates uncertainty, but the tool name and sibling functions (detect_pii, sanitize_document, sanitize_text) all perform non-destructive analysis/transformation.
From the tool's definition Tool name 'detokenize_text' suggests reversing tokenization, which is a read/analysis operation similar to the sanitize and detect tools on this server. The empty description is uninformative and lowers confidence.
Attacks that exploit this kind of access
detokenize_text. It is categorised as a Read tool in the Mcp Pii Guard Au MCP Server, which means it retrieves data without modifying state.
Register the Mcp Pii Guard Au MCP server in PolicyLayer and add a rule for detokenize_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.
detokenize_text is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the detokenize_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.
Set action: deny in the PolicyLayer policy for detokenize_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.
detokenize_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.
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 →