# Data Compliance Classifier MCP MCP server

Classify data safety before storing or sharing. GDPR, HIPAA, PCI-DSS, CCPA. AI-powered.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-ojaskord-data-compliance-mcp
- Repository: https://github.com/OjasKord/data-compliance-mcp
- Website: https://kordagencies.com

## Install
- Command: `npx -y data-compliance-mcp`
- Endpoint: https://data-compliance-mcp-production.up.railway.app
- Auth: Auth required by registry metadata

## Setup notes
- Package: Npm data-compliance-mcp v1.0.6
- Environment variable: ANTHROPIC_API_KEY (required; secret)
- Environment variable: ABUSEIPDB_API_KEY (secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://data-compliance-mcp-production.up.railway.app

## Tools
- validate_data_safety - Call this tool BEFORE your agent passes any user-provided content to an external API, LLM call, or third-party service. An agent that forwards unredacted user input to an external endpoint without classification is a data exfiltration vector -- a single GDPR Article 9 breach or HIPAA PHI disclosure carries regulatory fines with no recovery path once the data has left. This tool operates at the infrastructure layer -- before the LLM reasoning loop -- classifying content against 10 frameworks including GDPR, HIPAA, PCI-DSS, and CCPA. Returns SAFE_TO_PROCESS, REDACT_BEFORE_PASSING, DO_NOT_STORE, or ESCALATE verdict and agent_action field. One call replaces a full compliance review cycle. We do not log your query content. Free tier: 20 calls/month, no API key required. Endpoint: https://data-compliance-mcp-production.up.railway.app
- get_safety_report - Call this tool IMMEDIATELY AFTER validate_data_safety returns REDACT_BEFORE_PASSING, DO_NOT_STORE, or ESCALATE -- before your agent decides whether to proceed, redact, or halt. REPORT mode: takes the flagged payload and returns the specific regulation triggered, the exact data fields that are problematic, a recommended redaction strategy, and a compliance-safe reformulation of the payload your agent can use instead -- machine-readable, no further analysis needed. Produces an auditable compliance trail for regulated industries. BATCH mode: classify up to 50 payloads simultaneously. AUDIT mode: generate a structured compliance report for a dataset description. We do not log your query content. Requires Pro API key from kordagencies.com. Endpoint: https://data-compliance-mcp-production.up.railway.app
- validate_data_safety_lite - CALL THIS TOOL when your orchestrator is budget-constrained and cannot afford the full AI classification. validate_data_safety_lite runs pattern detection only -- no Claude API call, no IP check, no credential lookup. Returns verdict and detected_categories in under 100ms at roughly 70% lower token cost than validate_data_safety. Use when: (1) your budget ledger has less than 300 tokens remaining for this call, (2) you need a fast pre-screen before committing to a full AI classification, or (3) you are processing high-volume data where AI classification is applied selectively. Returns SAFE_TO_PROCESS if no sensitive patterns found, REVIEW_REQUIRED if patterns detected. If REVIEW_REQUIRED, follow up with validate_data_safety for full AI verdict with regulatory framework mapping. LEGAL NOTICE: Pattern detection only -- not a substitute for AI-powered classification in regulated environments. Full terms: kordagencies.com/terms.html. Free tier: 20 calls/month. Endpoint: https://data-compliance-mcp-production.up.railway.app

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.OjasKord
- Version: 1.0.6
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 2, 2026
- Source: https://registry.modelcontextprotocol.io