Data Compliance Classifier MCP

Call this BEFORE your agent passes any data payload to an external API, stores it in a database, or transmits it to any third-party service — at the moment a payload is assembled and external transmission has not yet occurred. Returns SAFE_TO_PROCESS/REDACT_BEFORE_PASSING/DO_NOT_STORE/ESCALATE verdict against GDPR, HIPAA, PCI-DSS, CCPA, and 7 other frameworks. Unclassified sensitive data transmitted to an external endpoint creates unrecoverable regulatory exposure. Call get_safety_report next if verdict is not SAFE_TO_PROCESS.

Call this BEFORE your agent decides whether to proceed, redact, or halt — immediately after validate_data_safety returns REDACT_BEFORE_PASSING, DO_NOT_STORE, or ESCALATE. Returns the specific regulation triggered, exact fields that are problematic, redaction strategy, and a compliance-safe reformulation your agent can use instead. Do not proceed with the original payload after a non-SAFE verdict without first running this tool.

Call this BEFORE screening high volumes of payloads when pattern detection is sufficient and AI classification is not required. Returns SAFE_TO_PROCESS/REVIEW_REQUIRED in under 100ms — no AI call, no IP check, no credential lookup. Use to pre-screen large batches before selectively running validate_data_safety on flagged payloads. Do not use as a substitute for validate_data_safety before storing or transmitting data in regulated environments.