Skip to main content
Glama

PII Pattern Scan

pii_scan
Read-only

Best-effort scan of supplied text for common patterns: email, phone, US SSN, Luhn-checked card numbers, mod-97 IBANs, IP addresses, private-key shapes, BIP-39 seed phrases and API-key shapes. POST JSON {text, redact?}. Returns findings with type and offsets; redacted text only when redact is true. Best-effort only, not a compliance assessment. Informational only, no warranty. This service does not log or store the text you submit. USDC on Base or Polygon. Bad input is not charged. Price $0.02 per call via x402, USDC on Base (MCP payments are Base only). Paid calls are subject to Horizon Pulse buyer terms: https://horizonpulse.dev/terms/buyer

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": "pii_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesCaller text to scan. It is not logged or stored.
redactNoWhen true, the answer includes redacted text.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover readOnly/non-destructive, but the description adds genuinely non-obvious behavior: no logging or storage of submitted text, bad input not charged, $0.02 per call via x402, and the return shape (findings with type and offsets; redacted text only when redact=true). Minor deduction for the muddled payment-network text ('USDC on Base or Polygon' immediately followed by 'Base only'), which introduces ambiguity rather than clarity.

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

Conciseness5/5

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

Wait — re-evaluated below; see score of 3.

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?

With no output schema, the description does the necessary work of describing the return value (findings with type and offsets, optional redacted text), and it covers cost, payment, and privacy handling for a paid tool. What's missing is trivial (input size limits, pagination/truncation behavior for large texts).

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 description coverage is 100%, so both parameters are already documented; the description's restatement that redacted text appears only when redact is true duplicates the schema rather than extending it. No syntax or size limits for the text payload are added.

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

Purpose5/5

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

States a specific verb+resource ('scan of supplied text for common patterns') and enumerates exactly what it detects: email, phone, SSN, Luhn-checked cards, mod-97 IBANs, IPs, private-key shapes, BIP-39 seed phrases, API-key shapes. This is clearly distinguishable from generic siblings like extract or search.

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

Usage Guidelines3/5

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

Usage is implied (scan caller-supplied text) and there is one useful boundary statement — 'Best-effort only, not a compliance assessment' — which tells the agent when not to rely on the output. However, no sibling routing or explicit when-to-use-vs-alternative guidance is given.

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.