F
licenseNot graded
qualityD
maintenanceEnables AI agents to redact PII from text, summarize redacted content, and manage custom redaction patterns across multiple languages.
-
fairquery-llm-data-guard
Officialby fairquery
Related Servers
Alternatives to fairquery-llm-data-guard
No user-submitted related servers found.
Related Servers
- AlicenseAqualityCmaintenanceDetects and redacts sensitive personal information such as names, emails, phone numbers, ID numbers, and locations in text before it is processed by AI agents, using configurable mask, hash, or remove strategies.1MIT
- FlicenseAqualityBmaintenancePII sanitization layer for autonomous AI agent pipelines. Detects and redacts emails, phone numbers, national IDs, private keys, and financial data before text reaches LLMs. Supports EN, ES (LATAM), PT (BR/PT), DE, JA.12-
classifinder-mcpofficial
AlicenseAqualityCmaintenanceEnables AI agents to scan text for leaked secrets and prompt injection markers, and redact them before reaching an LLM.21MIT- FlicenseNot gradedqualityFmaintenanceRedacts PII from LLM traces and tool payloads before they leave review, enabling PII scanning, payload redaction, sensitive field classification, privacy receipts, and trace audit exports.-
- AlicenseAqualityDmaintenanceScans prompts for PII and masks or redacts sensitive data locally before sending to an LLM, supporting multiple anonymization modes.1MIT
TDQS
A4.7/5.0
Scored across 4 tools
Disambiguation4/5
Each tool has a distinct role (scan, poll, list reference types, restore), and descriptions explicitly tell agents when to use one over another. The only real overlap is guard_text mode="restore" versus restore_placeholders, but the description flags this and steers agents to the free tool.
Naming Consistency5/5
All four names follow a clean verb_noun snake_case pattern (guard_text, get_run_results, list_detectors, restore_placeholders). No casing or verb-style deviations.
Tool Count4/5
Four tools is on the lean side but each maps to a distinct stage of the redact/restore round trip, so nothing feels redundant. It is well-scoped for the domain, though there is little slack.
Completeness4/5
The lifecycle (discover types -> detect/redact -> poll async run -> restore) is fully covered, including an async path and a free local restore. Minor gaps exist: no abort/run-management tool (explicitly deferred to the Apify console) and no OCR/image handling.
Maintenance
ActivityNo data
ResponsivenessSyncing