Skip to main content
Glama

eu_pii_scrubber_anonymizer

Read-onlyIdempotent

[Stateless sovereign PII scrubber. Pure regex & Luhn/MOD-97 calculation, read-only, side-effect free]. Detects and pseudonymizes European personal identifiable information (Codice Fiscale, EU VAT, IBANs, Luhn credit cards, emails, phone numbers, and IPv4/IPv6 addresses) strictly within local memory under GDPR Art. 4(5) and Art. 32. Usage: Use this tool to sanitize sensitive text, contracts, medical records, or support tickets before forwarding to external LLMs or third-party platforms. Returns: JSON object with { originalLength: number, sanitizedLength: number, detectedEntityCount: number, detectedEntityTypes: array, entities: array, sanitizedText: string, sovereignAudit: object }.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "eu_pii_scrubber_anonymizer"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesRaw input text containing potential European PII to inspect and sanitize
saltSecretNoOptional salt for deterministic HMAC hashing
replacementStrategyNoMasking strategy (default: PSEUDONYMIZATION)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint and idempotentHint already supplied, the description usefully adds that processing is stateless, regex/Luhn/MOD-97 based, in local memory only, and GDPR-framed. However, there is a soft tension worth noting: the schema says saltSecret is optional 'for deterministic HMAC hashing', implying default pseudonymization is salted randomly and therefore not byte-identical across calls, which sits uneasily with idempotentHint=true. The description does not resolve that ambiguity or mention input size limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with the safety profile, then usage, then returns — a sensible order with no filler sentences. The bracketed preamble is slightly dense and mixes guarantees with compliance citations, but each sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Because there is no output schema, the enumerated return fields (sanitizedText, entities, detectedEntityTypes, sovereignAudit, etc.) are genuinely necessary and are provided. Remaining gaps are minor: no guidance on maximum input length, behavior on partial/unmatched patterns, or how the audit object is structured.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so text, saltSecret, and replacementStrategy are all already documented at the field level; the baseline of 3 applies. The description adds no extra meaning about how saltSecret affects output determinism or how the three replacementStrategy modes differ in the returned entity records.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('detects and pseudonymizes') and an enumerated resource set (Codice Fiscale, EU VAT, IBANs, Luhn cards, emails, phones, IPv4/IPv6), so an agent knows exactly what the tool does. It does not, however, contrast itself against the closely named sibling eu_synthetic_data_masker, so sibling differentiation relies on the agent's own inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'Usage' sentence gives concrete triggering contexts (contracts, medical records, support tickets) and a clear purpose (before forwarding to external LLMs or third-party platforms). It stops short of stating when NOT to use it or naming an alternative masking tool for different needs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources