Skip to main content
Glama
multivon-ai

multivon-mcp

Official
by multivon-ai

eval_pii_detection

Scan LLM output for personally-identifiable information (PII) like emails, SSNs, and credit cards using local regex patterns. Returns a pass/fail score and lists detected PII types.

Instructions

Detect personally-identifiable information (PII) in an LLM output.

Local-first: zero API calls. Uses a regex pattern library covering emails, phone numbers, SSNs, credit cards, IBANs, IPs, addresses, and jurisdiction-specific identifiers (HIPAA MRNs, EU VAT, California bank accounts, etc).

Score 1.0 = no PII detected. Score 0.0 = PII found (the reason field lists which types matched and example substrings).

Args: output: The LLM-generated text to scan. jurisdiction: Which extra pattern set to include. One of "all" (default), "gdpr", "ccpa", "pipeda", or "hipaa". custom_patterns: Optional dict of {name: regex} to add to the default library (e.g. {"employee_id": r"EMP-\d{6}"}). redact: If True, replace matched substrings with [REDACTED-TYPE] markers in the reason field.

Returns: {"score": 0.0 or 1.0, "passed": bool, "reason": str, "threshold": float, "evaluator": "pii_detection"}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
outputYes
jurisdictionNoall
custom_patternsNo
redactNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

With no annotations provided, the description fully discloses behavioral traits: local-only operation, scoring (1.0 for no PII, 0.0 for PII found), and the redact feature. It adds value beyond the input schema by explaining the purpose and effects of parameters.

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?

The description is well-organized: a one-line purpose, a brief feature paragraph, scoring explanation, and a list of args. It is concise but not overly brief; each section adds useful information. Slight room for tightening, but overall effective.

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

Completeness5/5

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

The description covers all necessary aspects: purpose, usage context, parameter details, and a return format example. Given the presence of an output schema (context signal), the return values are explained, ensuring the agent has complete information to use the tool correctly.

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

Parameters5/5

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

Schema description coverage is 0%, but the description thoroughly explains each parameter: 'output' (text to scan), 'jurisdiction' (lists possible values), 'custom_patterns' (dict of name:regex), and 'redact' (boolean for replacements). This fully compensates for the lack of schema descriptions.

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?

The description clearly states the tool's action: 'Detect personally-identifiable information (PII) in an LLM output.' It identifies the specific resource (LLM output) and verb (detect), and differentiates from sibling eval tools by focusing on PII detection.

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 description notes 'Local-first: zero API calls,' implying safe deployment without external dependencies. It also explains jurisdiction and custom patterns options, providing context for use. However, it does not explicitly state when to avoid using this tool or compare to alternatives like toxicity detection.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/multivon-ai/multivon-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server