PII detection. POST { text }. Finds personally identifiable information — names, emails, phones, addresses, SSNs, credit cards, bank/IP/passport/DOB and more — returning each finding with its type and exact substring so you can redact it. For compliance, logging hygiene, and data-minimization bef...
AI agents call ai.pii to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only analysis tool that scans text to identify PII patterns and reports results. It does not create, modify, delete, or execute external operations. While it processes sensitive information (PII), the tool itself performs no destructive or write actions.
From the tool's definition Tool description states it 'Finds personally identifiable information' and returns 'each finding with its type and exact substring' — pure detection and analysis without modification.
Attacks that exploit this kind of access
PII detection. POST { text }. Finds personally identifiable information — names, emails, phones, addresses, SSNs, credit cards, bank/IP/passport/DOB and more — returning each finding with its type and exact substring so you can redact it. For compliance, logging hygiene, and data-minimization before storing or sending text. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for ai.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 Mcp. Nothing to install.
ai.pii 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 ai.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.
Set action: deny in the PolicyLayer policy for ai.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.
ai.pii is provided by the MCP server (@2sio/mcp). 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 →