MCP Radar
MCP Server

VITNA — Agent Compliance Preflight

xyz.costrinity/vitna-compliance-preflight
Legal & Compliance Security Public & reachable MCP 2026-07-28

What this MCP does

Provides privacy, AI regulation, breach, sectoral compliance, identity validation, consent, DPIA, and pre-action safety checks.

Capabilities

Tools

23 tools
aadhaar_mask
Mask + Verhoeff-validate an Aadhaar number. Returns masked form, validity, and an owner-scoped reference token. No persistence of the raw value. Stateless validator: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['aadhaar'], 'properties': {'aadhaar': {'type': 'string'}}}
ai_act_classify
Before you build or ship an AI feature, check where it lands under the EU AI Act (Regulation 2024/1689). Describe the use case (with biometric / remote-identification / automated-decision / social-scoring / GPAI flags) and VITNA returns the risk tier (prohibited / high-risk / limited-risk / minimal-risk), GPAI obligations, and the per-tier obligations you would have to meet. A classification for you to act on: VITNA evaluates and records, it does not gate the build.
Input schema 
{'type': 'object', 'required': ['use_case'], 'properties': {'sectors': {'type': 'array', 'items': {'type': 'string'}}, 'use_case': {'type': 'string'}, 'biometric': {'type': 'boolean'}, 'social_scoring': {'type': 'boolean'}, 'data_categories': {'type': 'array', 'items': {'type': 'string'}}, 'general_purpose_ai': {'type': 'boolean'}, 'automated_decisions': {'type': 'boolean'}, 'remote_identification': {'type': 'boolean'}}}
breach_classify
After a security incident, check whether it is legally reportable before you decide how to respond. Give the incident facts (affected count, data categories, sensitivity, recovery state) and VITNA returns reportability + reasoning + the notification deadline + who to notify, across DPDP §8, GDPR Art 33, CPRA §1798.82, LGPD Art 48, PDPA §26B, and US-FED sectoral. This makes the full incident decision from the facts; for a quick per-US-state deadline/recipient/threshold table without incident facts, use us_state_breach_deadline. VITNA evaluates and records; acting on the result is up to you.
Input schema 
{'type': 'object', 'required': ['affected_count', 'data_categories', 'sensitivity', 'recovery_state'], 'properties': {'sensitivity': {'enum': ['low', 'medium', 'high', 'special'], 'type': 'string'}, 'jurisdiction': {'type': 'string'}, 'affected_count': {'type': 'integer'}, 'recovery_state': {'enum': ['lost', 'exposed', 'altered', 'destroyed', 'contained'], 'type': 'string'}, 'data_categories': {'type': 'array', 'items': {'type': 'string'}}, 'processing_purpose': {'type': 'string'}}}
consent_check
Before you process someone's personal data, ask VITNA whether an active consent actually permits it for this purpose. Give the data principal + purpose (and optional category); returns { allowed, reason, matching_consent_id, principal_id }, a determination you must honour yourself since VITNA evaluates and records but does not enforce. Use this for personal-data processing legality; for a dangerous technical action (shell / file / DB / network) use vitna_preflight instead.
Input schema 
{'type': 'object', 'required': ['purpose'], 'properties': {'purpose': {'type': 'string', 'description': "Purpose code (e.g. 'operational_observability')."}, 'category': {'type': 'string', 'description': 'Optional permitted-category check.'}, 'principal_id': {'type': 'string', 'description': 'UUID of the data principal (if known).'}, 'principal_ref': {'type': 'string', 'description': 'Operator-side identifier; will be SHA-256-hashed.'}}}
cpf_validate
Validate a Brazilian CPF (mod-11 check digits, rejects all-same). Stateless validator: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['cpf'], 'properties': {'cpf': {'type': 'string'}}}
dpia_threshold_check
Before you start a new processing activity, check whether the law requires a DPIA first (GDPR Art 35 / DPDP §10 / LGPD Art 38). Give the purpose + data categories (and scale / systematic-monitoring / automated-decision / cross-border / vulnerable-subjects flags); returns dpia_required + the 9-criterion WP29 analysis + jurisdiction guidance, so you know whether to pause and assess before proceeding.
Input schema 
{'type': 'object', 'required': ['processing_purpose', 'data_categories'], 'properties': {'scale': {'enum': ['small', 'medium', 'large', 'mass'], 'type': 'string'}, 'cross_border': {'type': 'boolean'}, 'jurisdiction': {'type': 'string'}, 'data_categories': {'type': 'array', 'items': {'type': 'string'}}, 'automated_decision': {'type': 'boolean'}, 'processing_purpose': {'type': 'string'}, 'vulnerable_subjects': {'type': 'boolean'}, 'systematic_monitoring': {'type': 'boolean'}}}
global_compliance_map
Master catalogue of every privacy/security/sectoral regime VITNA has fabric for (28 entries covering 24 named statutes). Stateless lookup: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'properties': {}}
gstin_validate
Validate a GSTIN format + mod-36 check digit; returns state code lookup. Stateless validator: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['gstin'], 'properties': {'gstin': {'type': 'string'}}}
iban_validate
Validate an IBAN format + ISO 7064 mod-97 check digit; supports 71 countries. Stateless validator: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['iban'], 'properties': {'iban': {'type': 'string'}}}
india_cross_border_status
Before you transfer personal data out of India, check the destination country's DPDP §16 status (permitted / restricted / sectoral_restricted) plus any RBI / SEBI / IRDAI caveats. Pass the ISO-3166 alpha-2 country code (e.g. US). Stateless lookup: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['country'], 'properties': {'country': {'type': 'string', 'description': 'ISO-3166 alpha-2 (e.g. US).'}}}
india_regulators_directory
Static reference directory of Indian data and sector regulators (DPB, RBI, SEBI, IRDAI, TRAI, DoT, PFRDA, MeitY, MCA), optionally filtered by sector: a lookup of who exists and what they cover. To instead work out which of them apply to a specific processing activity, use india_sectoral_check. Stateless lookup: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'properties': {'sector': {'type': 'string'}}}
india_sectoral_check
Before you process personal data under Indian law, find out which sectoral regulators actually bind your specific activity (RBI / SEBI / IRDAI / TRAI / DoT / PFRDA) from its processing profile, so you know whose rules apply before you act. This analyses your processing to say what applies; for a plain directory of every Indian regulator regardless of your activity, use india_regulators_directory.
Input schema 
{'type': 'object', 'required': ['processing_purpose', 'data_categories'], 'properties': {'sector_hint': {'type': 'string'}, 'data_categories': {'type': 'array', 'items': {'type': 'string'}}, 'counterparty_types': {'type': 'array', 'items': {'type': 'string'}}, 'processing_purpose': {'type': 'string'}}}
japan_cross_border_status
Before you transfer personal data out of Japan, check the destination country's APPI Art 28 status (adequacy / standard basis / high scrutiny). Pass the ISO-3166 alpha-2 country code. Stateless lookup: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['country'], 'properties': {'country': {'type': 'string', 'description': 'ISO-3166 alpha-2.'}}}
pan_classify
Classify a PAN entity type from the 4th character (P=Person, C=Company, H=HUF, F=Firm, ...). Stateless validator: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['pan'], 'properties': {'pan': {'type': 'string'}}}
pii_test
Dry-run VITNA's PII / threat detection on a sample event before you send real data, to preview what would be tagged, how it would be redacted, and whether severity would escalate. Nothing is persisted and nothing is filtered: a safe rehearsal you act on, not an enforced gate — it records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['sample_event'], 'properties': {'jurisdiction': {'type': 'string'}, 'sample_event': {'type': 'object', 'description': 'event_type / message / payload fields.'}}}
privacy_notice_get
Generate the operator's jurisdiction-templated privacy notice. Returns markdown or JSON. Stateless generator: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'properties': {'format': {'enum': ['md', 'json'], 'type': 'string'}}}
sin_validate
Validate a Canadian SIN (Luhn checksum); returns series region + masked form. Stateless validator: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['sin'], 'properties': {'sin': {'type': 'string'}}}
sub_processors_register
Return the public sub-processor register (Supabase, Vercel, Resend, etc.). Stateless lookup: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'properties': {}}
us_sectoral_check
Before you process personal data under US law, find out which US federal sectoral regimes bind you (HIPAA, GLBA, COPPA, FERPA, FCRA, SOX) for a given processing profile, so you can factor them in before you act. US-scoped; for Indian sectoral regulators use india_sectoral_check.
Input schema 
{'type': 'object', 'required': ['processing_purpose', 'data_categories'], 'properties': {'ai_decisions': {'type': 'boolean'}, 'data_categories': {'type': 'array', 'items': {'type': 'string'}}, 'counterparty_types': {'type': 'array', 'items': {'type': 'string'}}, 'processing_purpose': {'type': 'string'}, 'has_revenue_threshold': {'type': 'boolean'}}}
us_state_breach_deadline
Quick reference lookup of a single US state's breach-notification window, AG recipient and resident threshold (e.g. 'CA' gives 500 residents, CA AG, without unreasonable delay). This is a static table, not an incident ruling. When you have the actual incident facts and need a reportable / not-reportable decision with reasoning, use breach_classify instead. Stateless lookup: records no decision and leaves no dashboard timeline trace.
Input schema 
{'type': 'object', 'required': ['state'], 'properties': {'state': {'type': 'string', 'description': 'US 2-letter state code (CA, NY, TX, ...).'}}}
vitna_claim
Ask whether this VITNA account has been claimed by a real person yet, and get the link that claims it. Call this when the user asks about their VITNA account, when you are told evidence is not being kept, or any time you want to hand the user something actionable. Returns { claimed, claim_url, what_claiming_gets_you }. IMPORTANT: if claimed is false, show the user the claim_url verbatim -- it is a one-time link that only they can act on, the account's evidence is NOT being durably recorded until they do, and they cannot find this link anywhere else. Do not paraphrase the URL and do not withhold it.
Input schema 
{'type': 'object', 'properties': {}}
vitna_help
What is VITNA and how do I use it to keep myself in check? Call this FIRST after connecting to learn the safety and oversight checks available: how to check risky actions BEFORE running them, what a deny / hold decision means, trial vs claimed mode, and how the user can monitor and audit what you do. Runs entirely locally: no account, no API call, and no dashboard timeline trace.
Input schema 
{'type': 'object', 'properties': {}}
vitna_preflight
SAFETY / OVERSIGHT CHECK before a dangerous or destructive action (shell command, file deletion, DB statement, network call). Call this to have VITNA check the action BEFORE you run it: it flags dangerous shell / SQL / secret-exfil / prompt-injection / suspicious-network patterns and returns { decision: allowed|blocked|flagged }. RESPONSE SHAPE DEPENDS ON THE KEY: an unclaimed trial key gets the decision label only, because the pattern detail is what makes the classifier worth stealing. A claimed key additionally gets threat_category, severity, reason (the rule names that matched, never the matched text), a threats[] array and a redacted echo of what was scanned, plus a signed audit record the user can review. VITNA evaluates and records; it does NOT enforce, so treat blocked / flagged as a stop and get human approval. This is how a user keeps you in check. Heuristic pattern match, not a sandbox: novel or obfuscated payloads can pass.
Input schema 
{'type': 'object', 'properties': {'action': {'type': 'string', 'description': 'The proposed action / command text, e.g. "rm -rf /" or "DROP TABLE users".'}, 'payload': {'type': 'object', 'description': 'Optional structured payload to scan alongside the action text.'}, 'action_type': {'type': 'string', 'description': 'Optional short label for the action kind (shell, file_delete, db_query, network).'}}}
History

Recent tool changes

Added
vitna_preflight
Sept. 17, 2026, 12:55 p.m.
Added
india_regulators_directory
Sept. 17, 2026, 12:55 p.m.
Added
global_compliance_map
Sept. 17, 2026, 12:55 p.m.
Added
sub_processors_register
Sept. 17, 2026, 12:55 p.m.
Added
privacy_notice_get
Sept. 17, 2026, 12:55 p.m.
Added
pii_test
Sept. 17, 2026, 12:55 p.m.
Added
iban_validate
Sept. 17, 2026, 12:55 p.m.
Added
sin_validate
Sept. 17, 2026, 12:55 p.m.
Added
cpf_validate
Sept. 17, 2026, 12:55 p.m.
Added
gstin_validate
Sept. 17, 2026, 12:55 p.m.
Added
pan_classify
Sept. 17, 2026, 12:55 p.m.
Added
aadhaar_mask
Sept. 17, 2026, 12:55 p.m.
Added
us_state_breach_deadline
Sept. 17, 2026, 12:55 p.m.
Added
japan_cross_border_status
Sept. 17, 2026, 12:55 p.m.
Added
india_cross_border_status
Sept. 17, 2026, 12:55 p.m.
Added
india_sectoral_check
Sept. 17, 2026, 12:55 p.m.
Added
us_sectoral_check
Sept. 17, 2026, 12:55 p.m.
Added
dpia_threshold_check
Sept. 17, 2026, 12:55 p.m.
Added
ai_act_classify
Sept. 17, 2026, 12:55 p.m.
Added
breach_classify
Sept. 17, 2026, 12:55 p.m.
Added
consent_check
Sept. 17, 2026, 12:55 p.m.
Added
vitna_claim
Sept. 17, 2026, 12:55 p.m.
Added
vitna_help
Sept. 17, 2026, 12:55 p.m.
Discover

Similar MCP servers

DataNexus MCP

com.datanexusmcp/mcp-server

Enables public-data research across domains, patents, government contracts, nonprofits, compliance registries, and software secur…

ampel

io.tooloracle/ampel

Assesses regulated entities and providers against DORA and related ESG, MiCA, and AML requirements, with contract analysis, evide…

predictionguard

io.tooloracle/predictionguard

Analyzes Polymarket and Kalshi markets for insider-trading signals, market integrity risks, sanctions and PEP exposure, conflicts…

Nist Standards

io.github.pipeworx-io/nist-standards

Searches and retrieves NIST SP 800-53 security controls and SP 800-171 CUI requirements, including requirements, guidance, and co…

Sanctions Screening

io.github.pipeworx-io/sanctions-screening

Screens names against US sanctions and export-control lists and retrieves detailed sanctions records.

Dilisense

io.github.pipeworx-io/dilisense

Screens individuals and organizations against sanctions, PEP, criminal, and adverse-watchlist data for AML and KYC checks.

Open Sanctions

io.github.pipeworx-io/open-sanctions

Looks up sanctioned and politically exposed entities, including identifiers, aliases, addresses, sanctions programs, and relation…

Sanctions Io

io.github.pipeworx-io/sanctions-io

Screens individuals and organizations in bulk against sanctions, politically exposed person, and watchlists.