MCP servers tagged pii
38 live MCP servers tagged "pii", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with pii.
Vigils
A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.
Spring AI Privacy Guardrails
Privacy guardrails for Spring AI: request-scoped PII tokenization and least-privilege disclosure across model/tool calls, with Presidio and JVM-local OpenNLP.
CloakLLM
Open-source PII cloaking + tamper-evident audit logs for LLM API calls
Anonymize
Path-only local MCP server for stella PII anonymization
Security Proxy
Security proxy for MCP servers — intercepts tool calls, detects prompt injection, masks PII, and writes audit logs
Pii MCP
Scrub PII before it reaches AI
Exodus Ia Firewall
🛡️ Local privacy firewall for AI coding agents — masks API keys & personal data before they reach the cloud, then restores them transparently.
AMazeControlPlane
Open-source AI Agent Control Plane for runtime MCP security, policy enforcement, PII protection, tool governance, and audit logging. Runtime control plane for AI agents. Every LLM…
Redacted Context MCP
Read-only, redacted local knowledgebase context for coding agents.
Pii Guard Au
MCP server for Australian PII detection — TFN, Medicare, ABN with checksum validation. Compliance audit logging for Australian Privacy Act, GDPR, HIPAA. Built on Presidio + spaCy.
Haechi
Experimental self-hosted AI context enforcement layer for LLM, MCP, vLLM, Ollama, and agent traffic.
Maskingtape
한국어 개인정보 비식별화 오픈소스 엔진 — 규칙+로컬 LLM 하이브리드 PII 탐지·마스킹 라이브러리, CLI, MCP 서버 (2026 오픈소스 개발자대회, 팀 마스킹테이프)
Tailrace
Agent data governance for TypeScript. In-process secret/PII detection, reversible tokenization, and policy at the model, tool, and MCP boundaries.
Privacyshell
Hardened browser profile generator — Firefox / LibreWolf / Brave
Privacyfence
Open-source privacy and approval gateway for AI assistants (MCP): human approval, local PII checks and audit for Gmail, Drive, Slack, Salesforce, Jira and more.
Myrmion Blackbar Pii Guard
🛡️ PII redaction for Claude, powered by Microsoft Presidio — automatic in Claude Code, on-demand in Claude Desktop.
Pii Anonymizer
Anonymize sensitive PII data from text
Deidproof
Re-identification risk assessment that computes k-anonymity, l-diversity, and HIPAA Safe Harbor compliance on a dataset.
Piicomb
Local PII discovery in your own files — SSN/CC/passport/DL/email/phone/DOB
Philter MCP
Redact PII and PHI from your AI agents with Philter, over the Model Context Protocol.
Privacy Filter Module
Drop-in PII detection & redaction for Python. Regex + heuristics + optional ML model. Use as a library, local REST API, or MCP server for Claude — offline by default, nothing logg…
Metascrub
Strip identifying metadata from docs/images before release
Promptguard MCP
Local-first MCP server that scans developer prompts for secrets, PII and token cost before they reach the LLM. TypeScript, with VS Code and browser extensions.
Cloak
Local, reversible secret & PII redaction proxy for MCP traffic — masks API keys/PII in JSON-RPC both directions with an audit log, and restores real values locally for debugging.
Openmasq
Privacy-first desktop chat for multiple LLMs: sensitive values are redacted on-device before any network call, and restored in the reply. Your own keys, a local model, or a CLI su…
Noren
A lightweight AI security layer, inspired by Japanese noren, protecting without closing the door.
Cover MCP
Cover for Claude Desktop. Redact PII from PDFs locally via MCP; documents never leave your Mac.
Healthcare Redaction MCP
Scalable engine for detecting and redacting PHI/PII from healthcare documents and data streams. Supports OCR and NLP-based extraction, configurable redaction rules, audit logging,…
Questa MCP
Questa Privacy MCP — anonymize and redact PII before it reaches AI models.
Privacyspoof
AdGuard/uBlock blocklists + UA/geo/cookie/session spoofing with a browser compatibility matrix
Trackblock
Family phone stalkerware audit — MVT-class iOS/Android forensics
Lineagemap
Column-level lineage extracted from SQL and dbt
Cloakbox
Run LLMs on sensitive data safely: a DuckDB privacy gateway with deterministic tokenization, fail-closed validation, and an isolated re-identification decoder.
Bugsafe
Share bugs, not secrets
Claude Triage
PII-safe, audit-logged triage agent — a minimal Forward-Deployed reference for Claude tool-use + evals. Live demo at claude-triage.vercel.app
Hybrid MCP Hub
Local-first AI agent that routes queries between Ollama (local) and Groq (cloud) based on PII. LangGraph, MCP, Presidio. Test project, not actively maintained.
Pi Secrets Guard
Block secrets and PII before they land: regex + entropy scanning for files, diffs, and AI coding agents (CLI + MCP + skill + pi extension).
Patton
No description published.