pii-safe-db-mcp

Scan table for PII

pii_scan

Read-only

Samples table rows and reports which columns contain PII by name and detected values, returning counts only to uncover hidden PII in free-text fields.

Instructions

Sample rows from a table and report which columns contain PII (by column name and by detected values). Returns counts only, never values. Use it to discover PII hiding in free-text columns.

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": {
      "table": "<table>"
    },
    "name": "pii_scan"
  }
}

Input Schema

Name	Required	Description	Default
`table`	Yes	Table name, optionally schema-qualified.
`sample_size`	No	Rows to sample (default 200).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 7, 2026

TDQS

A3.8/5.0

Behavior4/5

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

readOnlyHint=true already covers the safety profile, but the description adds genuinely non-obvious behavior: it samples rather than scanning exhaustively, and it returns counts only, never values. That privacy guarantee is the key thing an agent needs to know before calling. It omits cost/latency implications of a large sample_size and failure behavior on inaccessible tables.

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?

Two tight sentences: the first establishes what is done and what is returned, the second establishes the key constraint (counts, not values) and the intended use case. Nothing is redundant and the most important guarantee is front-loaded.

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 usefully compensates by explaining the return shape (per-column PII findings, by name and by detected values, counts only). Parameters are covered by the schema. The remaining gap is operational context such as permissions needed or behavior on very large or unreadable tables.

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%, with both table and sample_size fully documented including bounds and the default of 200, so the schema carries the burden. The description reinforces the sampling concept but adds no syntax or semantics beyond what the schema states, making the baseline 3 correct.

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?

States a specific action chain: sample rows from a table, then report which columns contain PII, and specifies both detection methods (column name and detected values). It implicitly separates itself from describe_table by targeting detected values in free-text, but never names a sibling tool explicitly, so it stops short of a 5.

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?

"Use it to discover PII hiding in free-text columns" gives a genuine use case, which is more than nothing. However, there is no guidance on when to prefer describe_table or query instead, no exclusions, and no note on prerequisites such as needing read access to the table.

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

Deploy Server