Claude MarketplacesSubmit
ojaskord avatar

Data Compliance Classifier MCP

ojaskord/data-compliance-mcp

This is a pre-action validator for agents that need to classify data payloads before storing or transmitting them. The validate_data_safety tool scans for PII, detects which regulations apply (GDPR, HIPAA, CCPA, PCI-DSS), checks credential breach exposure via AbuseIPDB, and returns a SAFE_TO_PROCESS, ESCALATE, or DO_NOT_STORE verdict with jurisdiction detection. You'd call it before your agent commits user data to a database, sends it to a third-party API, or includes it in a generated report. Free tier gives you 20 calls per month over streamable HTTP, so no local installation. The paid tier adds batch validation for up to 50 payloads and full audit reports.

tools
3
auth
Secret needed
transport
STDIO, HTTP
env vars
2
last updated
Jun 25, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://data-compliance-mcp-production.up.railway.app --name data-compliance-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http data-compliance-mcp https://data-compliance-mcp-production.up.railway.app

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 3 tools

Verified live against the running server on Nov 6, 2026.

validate_data_safetyValidates a data payload against GDPR, HIPAA, PCI-DSS, and other frameworks. Call this BEFORE your agent passes any assembled payload to an external API, writes it to a database, or transmits it via any third-party service -- at the moment the payload is assembled and no exter...4 params

Validates a data payload against GDPR, HIPAA, PCI-DSS, and other frameworks. Call this BEFORE your agent passes any assembled payload to an external API, writes it to a database, or transmits it via any third-party service -- at the moment the payload is assembled and no exter...

Parameters* required
contextstring
What your agent is about to do with this data (e.g. "write to database", "send to third-party API", "log to file", "pass to email tool"). Improves verdict accuracy.
data_origin_ipstring
IP address of the data subject or data source. Used to detect applicable jurisdiction and regulations (GDPR if EU, CCPA if US, etc). Optional but improves regulatory accuracy.
jurisdictionstring
Override jurisdiction if known (e.g. "EU", "US", "UK", "CA", "AU"). Use if data_origin_ip is unavailable but jurisdiction is known.
payload*string
The data payload to classify. Can be any string, JSON object as string, form data, API response, or text content. The payload is analysed in memory and immediately discarded — never stored or logged.
get_safety_reportRetrieves a detailed compliance report and remediation strategy for a flagged payload. 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. Use this when vali...6 params

Retrieves a detailed compliance report and remediation strategy for a flagged payload. 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. Use this when vali...

Parameters* required
contextstring
What will be done with this data. Used to improve verdict accuracy.
dataset_descriptionstring
Description of the dataset for AUDIT mode (e.g. "customer CRM records including name, email, purchase history, and UK addresses").
jurisdictionstring
Jurisdiction override for REPORT mode (e.g. "EU", "US", "UK"). Optional.
mode*string
REPORT: get redaction strategy and compliant reformulation for a flagged payload. BATCH: classify up to 50 payloads. AUDIT: generate compliance summary report.one of REPORT · BATCH · AUDIT
payloadstring
The flagged payload to analyse. Required for REPORT mode.
payloadsarray
Array of data payloads to classify. Required for BATCH mode. Maximum 50.
validate_data_safety_liteValidates a payload for sensitive patterns without AI classification. Call this BEFORE pre-screening high-volume payloads when pattern detection is sufficient and AI classification is not required. Use this when your agent is processing a large volume of payloads in batch and...2 params

Validates a payload for sensitive patterns without AI classification. Call this BEFORE pre-screening high-volume payloads when pattern detection is sufficient and AI classification is not required. Use this when your agent is processing a large volume of payloads in batch and...

Parameters* required
contextstring
Optional: what your agent plans to do with this data.
payload*string
The data payload to screen for sensitive patterns.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

ANTHROPIC_API_KEY*secret

Anthropic API key for AI classification

ABUSEIPDB_API_KEYsecret

AbuseIPDB API key for threat intelligence (optional)

Readme

smithery badge

Data Compliance Classifier MCP

ToolRank

Your agent is about to store customer data. Is it safe to? This tool tells you in one call.

What it does

Before 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.

Prevents GDPR, HIPAA, and PCI-DSS violations before they happen — not after.

Why this exists

Autonomous 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.

This tool gives agents a pre-action safety check. One call, clear verdict, agent proceeds or halts.

Tools

validate_data_safety (free tier)

View the full README on GitHub

Details

Repository
github.com/ojaskord/data-compliance-mcp
Website
kordagencies.com
Category
Data & Analytics
Package
data-compliance-mcp
Transport
STDIO, HTTP
Auth
Required
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from ojaskord

Related Data & Analytics MCP servers

View all
1sofiajameson20-star avatarNordic Datasofiajameson20-star/nordicdataGlobal B2B intelligence for AI agents: 35M+ companies, 1.6M sanctions, KYB pack. 78 tools.0stars
2zev-lll avatarLastLook Datazev-lll/lastlook-dataFRED macro data, Treasury yields, FX rates & macro indicators for AI agents. Pay-per-query via x402.0stars
3googleanalytics avatarAnalyticsgoogleanalytics/google-analytics-mcpProvides access to Google Analytics data and reports via an MCP API surface.2.1Kstars
43121n avatarStatfin Mcp3121n/nor-data-statfin-mcpStatistics Finland (StatFin/PxWeb): search tables, read metadata, fetch JSON-stat2 data.0stars
5rbmuller avatarScherlokrbmuller/scherlokZero-config data-quality monitoring: profile a warehouse, detect anomalies, gate CI.14stars
6xjtlumedia avatarMarkdown Formatterxjtlumedia/ai_answer_copierAI Answer Copier — Convert Markdown to PDF, DOCX, HTML, LaTeX, CSV, JSON, XML, XLSX, RTF, PNG0stars