{
  "markdown": "[![smithery badge](https://smithery.ai/badge/OjasKord/data-compliance-mcp)](https://smithery.ai/servers/OjasKord/data-compliance-mcp)\n\n# Data Compliance Classifier MCP\n\n[![ToolRank](https://toolrank.dev/badge/dominant.svg)](https://toolrank.dev/ranking)\n\nYour agent is about to store customer data. Is it safe to? This tool tells you in one call.\n\n## What it does\n\nBefore your agent stores, transmits, logs, or passes any data to another system — call `validate_data_safety`. Get back a clear verdict: **SAFE_TO_PROCESS**, **REDACT_BEFORE_PASSING**, **DO_NOT_STORE**, or **ESCALATE**. Your agent acts on the verdict immediately. No human interpretation needed.\n\nPrevents GDPR, HIPAA, and PCI-DSS violations before they happen — not after.\n\n## Why this exists\n\nAutonomous agents handle data from users, APIs, forms, and external sources constantly. Most agents process that data without checking whether they should. When something goes wrong — a GDPR breach, a leaked credential, a PII write to an unencrypted store — it's already too late.\n\nThis tool gives agents a pre-action safety check. One call, clear verdict, agent proceeds or halts.\n\n## Tools\n\n### `validate_data_safety` (free tier)\n\nCall this BEFORE your agent stores, transmits, or passes any data payload.\n\n**Input:**\n- `payload` — the data to classify (any string, JSON, form data, API response)\n- `context` — what your agent is about to do with it (improves accuracy)\n- `data_origin_ip` — optional IP for jurisdiction detection (GDPR if EU, CCPA if US, etc.)\n- `jurisdiction` — optional override if IP unavailable\n\n**Output:**\n- `verdict` — SAFE_TO_PROCESS / REDACT_BEFORE_PASSING / DO_NOT_STORE / ESCALATE\n- `sensitivity_level` — PUBLIC / INTERNAL / CONFIDENTIAL / RESTRICTED\n- `detected_categories` — PII, PHI, PCI, CREDENTIALS, FINANCIAL, LOCATION, etc.\n- `applicable_regulations` — GDPR, HIPAA, PCI-DSS, CCPA, PIPEDA, LGPD, etc.\n- `recommended_action` — one sentence telling your agent exactly what to do next\n- `jurisdiction_detected` — country detected from IP\n- `credential_check` — breach status from HaveIBeenPwned k-anonymity API\n- `patterns_detected` — pre-screened PII patterns found\n\n### `get_safety_report` (paid tier)\n\nBatch classification for up to 50 payloads plus audit-ready compliance reports.\n\n**Modes:**\n- `BATCH` — classify multiple payloads with full AI reasoning + AbuseIPDB threat intelligence\n- `AUDIT` — generate a structured compliance report for a dataset description\n\n### `validate_data_safety_lite` (free tier)\n\nPattern-only screening for high-volume payload batches -- no AI classification, no IP check, no jurisdiction lookup. Returns SAFE_TO_PROCESS / REVIEW_REQUIRED in under 100ms. Use to filter large batches before selectively running `validate_data_safety` on flagged items.\n\n## Data privacy\n\nWe do not store or log your data payloads. All payloads are analysed in memory and immediately discarded. Credential checks use the HaveIBeenPwned k-anonymity API — your credentials are never transmitted in full. Only the first 5 characters of a SHA-1 hash are sent.\n\n## Data sources\n\n- **Claude AI** — sensitivity classification and regulatory mapping\n- **IPinfo** (ipinfo.io) — jurisdiction detection from IP address\n- **HaveIBeenPwned** (haveibeenpwned.com) — credential breach checking via k-anonymity\n- **AbuseIPDB** (abuseipdb.com) — IP threat intelligence (paid tier)\n\n## Pricing\n\n| Plan | Classifications | Price |\n|---|---|---|\n| Free | 20/month | No API key needed |\n| Starter | 500-call bundle | $24 |\n| Pro | 2,000-call bundle | $84 |\n\nUpgrade at [kordagencies.com](https://kordagencies.com)\n\n## Quick start\n\nNo API key needed for free tier:\n\n```json\n{\n  \"data-compliance\": {\n    \"url\": \"https://data-compliance-mcp-production.up.railway.app\"\n  }\n}\n```\n\nWith paid API key:\n\n```json\n{\n  \"data-compliance\": {\n    \"url\": \"https://data-compliance-mcp-production.up.railway.app\",\n    \"headers\": {\n      \"x-api-key\": \"your_api_key_here\"\n    }\n  }\n}\n```\n\n## Harness Integration\n\n### Claude Code / Claude Desktop (.mcp.json)\n```json\n{\n  \"mcpServers\": {\n    \"data-compliance\": {\n      \"type\": \"http\",\n      \"url\": \"https://data-compliance-mcp-production.up.railway.app\"\n    }\n  }\n}\n```\n\n### LangChain (Python)\n```python\nfrom langchain_mcp_adapters.client import MultiServerMCPClient\nclient = MultiServerMCPClient({\n    \"data-compliance\": {\n        \"url\": \"https://data-compliance-mcp-production.up.railway.app\",\n        \"transport\": \"http\"\n    }\n})\ntools = await client.get_tools()\n```\n\n### OpenAI Agents SDK (Python)\n```python\nfrom agents import Agent, HostedMCPTool\nagent = Agent(\n    name=\"Assistant\",\n    tools=[HostedMCPTool(tool_config={\n        \"type\": \"mcp\",\n        \"server_label\": \"data-compliance\",\n        \"server_url\": \"https://data-compliance-mcp-production.up.railway.app\",\n        \"require_approval\": \"never\"\n    })]\n)\n```\n\n### LangGraph\nSame as LangChain above — langchain-mcp-adapters works with LangGraph natively.\n\n## Example call\n\n```bash\ncurl -X POST https://data-compliance-mcp-production.up.railway.app \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/call\",\"params\":{\"name\":\"validate_data_safety\",\"arguments\":{\"payload\":\"{\\\"name\\\":\\\"John Smith\\\",\\\"email\\\":\\\"john@example.com\\\",\\\"dob\\\":\\\"1985-03-12\\\",\\\"address\\\":\\\"14 Baker Street, London\\\"}\",\"context\":\"write to customer database\",\"jurisdiction\":\"EU\"}}}'\n```\n\nExpected response:\n```json\n{\n  \"verdict\": \"DO_NOT_STORE\",\n  \"sensitivity_level\": \"RESTRICTED\",\n  \"detected_categories\": [\"PII\"],\n  \"applicable_regulations\": [\"GDPR\"],\n  \"recommended_action\": \"Do not store without explicit consent and a documented lawful basis under GDPR Article 6.\",\n  \"jurisdiction_detected\": \"EU\"\n}\n```\n\n## Legal\n\nClassification is AI-powered and for informational purposes only. Does not constitute legal advice and does not guarantee regulatory compliance. Full terms: [kordagencies.com/terms.html](https://kordagencies.com/terms.html)\n",
  "bytes": 5931,
  "sha": "bf2df4260f8a40872685cabb01fe1b634fd3a1388f146de69aa8516d7b3b3405",
  "repo_slug": "ojaskord/data-compliance-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_ojaskord_data_compliance_mcp_5fd8aed9/readme"
}