Skip to main content
Glama
Sign In
MCPg - Production-grade PostgreSQL MCP Server

MCPg - Production-grade PostgreSQL MCP Server

by devopam
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Find sensitive columns

find_sensitive_columns
Read-only

Flags PostgreSQL columns whose names or types suggest sensitive data such as credentials, PII, financial, or health info, returning heuristic findings with confidence levels for a first review pass.

Instructions

Flag columns whose names or types look like they hold sensitive data (passwords, tokens, PII, financial info, health records). Pure heuristic — no row sampling, no value introspection. Categories: credential, financial, contact, identifier, health, government_id, location. Each finding carries a confidence (high / medium / low) so an agent can filter for a first review pass. Treat as a SIGNAL, not a verdict — a column named email_template_id matches the email pattern but isn't itself an email address. Returns an object with findings (list of {schema, table, column, data_type, category, confidence, matched_pattern}) and summary counts by category.

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": {
      "schema": "<schema>"
    },
    "name": "find_sensitive_columns"
  }
}

Input Schema

NameRequiredDescriptionDefault
schemaYes
databaseNoOptional: a database id from list_databases, to target a configured secondary (read-only) database; omit for the primary. Database names that are not configured ids are rejected.

Output Schema

NameRequiredDescriptionDefault
schemaYes
columnsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.4
    • changedInput schema / properties / database / description
      Previous value: -"Optional: target a configured secondary (read-only) database by name; omit for the primary. Call list_databases to see the configured ids."New value: +"Optional: a database id from list_databases, to target a configured secondary (read-only) database; omit for the primary. Database names that are not configured ids are rejected."
  2. First observedv0.6.8

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, it discloses the core behavioral trait: pure name/type heuristic with no row sampling or value introspection, plus a concrete false-positive example (email_template_id). The confidence tiers and category list give the agent the vocabulary it needs to triage output.

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?

Front-loaded with the core behavior, then heuristics, then categories, confidence, and caveats — a logical order with little waste. The closing sentence re-describes the return object, which duplicates the output schema rather than earning its place.

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?

For a read-only heuristic scanner, the description covers mechanism, output categories, confidence semantics, and pitfalls, and annotations plus an output schema handle safety and return shape. The remaining gap is scope — whether it scans every table in the given schema, and any cost/latency implications.

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

Parameters2/5

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

Schema coverage is only 50%: the `database` param is well documented in the schema, but `schema` has no schema description and the tool description never clarifies what it accepts or whether the scan is limited to that one schema. The description mentions no parameters at all, so it fails to compensate for the coverage gap.

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 and resource — 'flag columns whose names or types look like they hold sensitive data' — and enumerates the categories it recognizes. This clearly separates it from siblings like audit_database, lint_naming_conventions, or run_advisors, which an agent might otherwise confuse it with.

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?

Provides real usage context: 'so an agent can filter for a first review pass' and 'treat as a SIGNAL, not a verdict,' which tells the agent how much weight to put on results. It does not, however, name an alternative tool or state explicit when-not-to-use conditions relative to the many audit/lint siblings.

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

Deploy Server

Other Tools