Skip to main content
Glama
privacyscrubber-mcp

privacyscrubber-mcp

Sanitize PII & Secrets Locally (ZTDS RFC v1.0)

ztds_sanitize
Idempotent

Redacts PII, PHI, and credentials locally in RAM before sending text to an LLM, using reversible session-scoped surrogate tokens with zero network egress.

Instructions

Drop-in ZTDS RFC v1.0 sanitization tool. Redacts sensitive PII, PHI, and credentials locally in process RAM using deterministic reversible surrogate tokens, scoped to sessionId, with zero network egress.

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": "ztds_sanitize"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesRaw UTF-8 plain text, code, or log content to sanitize locally in RAM before sending to an LLM.
sectorNoOptional alias for 'profile'. The industry sector or compliance vertical to apply (e.g. 'medical', 'finance', 'legal', 'dev', 'hr', 'accounting', 'security', 'compliance', 'underwriting', 'telecom').
profileNoThe detection profile to use. Available: 'General' (Free, 15,000 chars), or 30 specialized industry profiles (5,000 chars Free trial quota; unlimited on PRO/TEAMS/SDK): 'Dev' (Engineering/Code), 'Medical', 'Pharma', 'Biotech', 'Telecom', 'Legal', 'Compliance', 'CCPA', 'Finance', 'Bizops', 'Sales', 'WealthMgmt', 'Insurance', 'Accounting', 'Underwriting', 'Automotive', 'Energy', 'Hospitality', 'HR', 'Security', 'Marketing', 'Support', 'RealEstate', 'Agents', 'Academic', 'Creative', 'Tech', 'Personal', 'Engineering'. Defaults to 'General'.
sessionIdNoOptional session identifier scoping the volatile RAM token map. Defaults to 'default'.default

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.5.1

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and openWorldHint=false, but the description adds genuinely new behavior: redaction is reversible via surrogate tokens, the token map is scoped to sessionId, and there is zero network egress. The reversibility and session-scoping details are non-obvious and materially affect how an agent sequences calls (e.g., pairing with ztds_restore).

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?

A single dense sentence with the core capability front-loaded and no wasted clauses. The 'Drop-in ZTDS RFC v1.0' branding is slightly promotional but still communicates a compliance-relevant standard.

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

Completeness3/5

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

With four parameters, no output schema, and full schema coverage, the definition covers input adequately but never says what the call returns (sanitized text plus tokens? a token map handle?) or how quota limits behave on failure. For a tool whose output is consumed downstream by restore, that omission leaves a real gap.

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 the text, profile/sector, and sessionId parameters are already fully documented, including the profile list and default. The description only restates that tokens are scoped to sessionId, adding no syntax, format, or validation detail beyond the schema; baseline 3 applies.

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?

Names a concrete action (redacts PII, PHI, credentials) and a concrete mechanism (local, in-RAM, reversible surrogate tokens), so the agent knows exactly what the tool does. It does not differentiate itself from close siblings such as sanitize_text, sanitize_file, or redact_file, leaving the boundary between them unstated.

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

Usage Guidelines2/5

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

The description gives no explicit when-to-use or when-not-to-use guidance and never names an alternative, even though sanitize_text, sanitize_file, and audit_directory_for_pii clearly overlap. The 'before sending to an LLM' context appears only in the schema's text parameter, not in the description itself.

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