- PDF Redaction MCP @pdf-redaction/pdf-redaction-mcpMCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.4 GitHub stars.
- AgentSQL @cuipengdba/agentsqlGuard AI agents' PostgreSQL/MySQL access via MCP: SQL audit, auth, masking, write approval5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.3 GitHub stars.
- WhitePact @guruprasath-annadurai/whitepactAI governance MCP server: trust scoring, guardrails, bias/hallucination detection, compliance.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 GitHub stars.
- APICK Identity @apick/identityKorean ID document verification and PII masking APIs12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Rightis @backers-shawn/rightisIdentity-rights registry lookups before AI generation: is a face, voice or persona registered?4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Compliance Check @hatchloop/compliance-checkPreview a TCPA/GDPR/CASL/10DLC gate result before spending a paid send. No key needed.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- CertScore.ai MCP Light @certscore/mcp-lightFree website privacy scanner for pre-consent cookies, trackers, consent, policy, and HTTPS/TLS.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Overwing @overwing/mcpGuardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- VITNA – Containment for rogue AI agents @costrinity/vitna-compliance-preflightGuard wraps stdio MCP servers: risky calls wait for a person; no answer, no run. Remote: cooperative5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Policyforge MCP @policyforge/mcpGenerate, audit, and maintain legal policies that match what your code actually does.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- HealthGuard @tooloracle/healthguardHealthGuard - 12-tool health/medical AI safety MCP: PII redaction, HIPAA, GDPR Art.9.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Prompt Compass @rishabhmpc/prompt-compassDecision-only prompt routing and firewall checks for local/cloud routing, PII and jailbreak risk.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Sigma Gate @spektre-labs/sigma-gateDeterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MyDataPass @mydatapass/mydatapassNeutral escrow for customer-data offboarding (GDPR/EU Data Act): query MyDataPass facts.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- LexVibe @marcosnovo/lexvibeOne-step legal compliance for vibe-coded apps: privacy, terms, cookie banner and EU AI Act check.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- QueryQuarry @queryquarry/queryquarryDouble-blind talent marketplace: AIs search anonymous opted-in candidates; reveal on consent.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Data Compliance Classifier MCP @ojaskord/data-compliance-mcpClassify data safety before storing or sharing. GDPR, HIPAA, PCI-DSS, CCPA. AI-powered.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Memra @usememra/memraPersistent memory for AI agents. EU-hosted, privacy-first, hybrid recall, contradiction detection.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Syntitan @syntitan/syntitan-mcpAI-Ready Data Platform that fills the missing layer between data management and AI execution.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Nexus @nexus-api-lab/nexus-mcpJapanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Ai Guardrails @lazymac2x/ai-guardrailsCloudflare Workers MCP server: ai-guardrails4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
Data privacy MCP servers
A server here detects or redacts personal data (PII), consent management or privacy law.
Not here: general security and servers that merely promise privacy.
155 remote220 localTagged by Odel's AI, which can make mistakes
Most popular in Data privacy
By GitHub stars, at most two per publisher- Number 1: KDAN PDF@kdandoc/kdan-pdf-mcpUpload, edit, compress, protect, redact, and compare PDFs with KDAN PDF in Claude and ChatGPT.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.57 GitHub stars.
- Number 2: HealthClaw Guardrails@aks129/healthclaw-guardrailsGuardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.31 GitHub stars.
- Number 3: EU AI Act@ark-forge/mcp-eu-ai-actEU AI Act + GDPR compliance scanner. One call, no arguments, 10 seconds. 22 AI frameworks detected.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.11 GitHub stars.
