MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
eu-pii-redactactive
Redact European personal data (names, national IDs, IBANs, emails, phones) before it reaches an LLM, and restore it afterwards. Python client and MCP server.
pypi MIT -
Enterprise Regulatory Compliance & Multi-Pattern PII Redaction Sentinel (inspired by Tencent Cloud Data Governance & GDPR/HIPAA Enterprise Policies). Detects and sanitizes personally identifiable information, financial account numbers, JWT tokens, and cryptographic keys using deterministic zero-leakage masking.
MIT -
eu-pii-redactgithub.com/JulianJohansen/eu-pii-redactno update data
Redact European personal data before it reaches an LLM, and restore it later. Replaces names, national ID numbers from 21 EU/EEA countries (validated by check digit and birth date), IBANs, cards, EU VAT numbers, emails, phones and IPs with placeholders like [PERSON_1]. redact_file and restore_file process files without the personal data ever entering the conversation. Needs a RapidAPI key for the EU PII Redaction API; the free plan gives 500 requests a month: https://rapidapi.com/JulianJohansen/api/eu-pii-redaction
smithery -
phi-redact-mcpgithub.com/rinava/phi-mcpupdated this year
Fail-closed MCP server that redacts PII/PHI from text before it reaches an LLM — self-hosted, no egress, HIPAA-aware.
pypi MIT -
pii-redactor-mcpupdated this year
MCP server for PII Redactor — redact personally identifiable information via AI assistants
npm MIT -
MCP server for Redact PDF AI — permanently redact PII from PDFs. The text is removed, not covered.
npm MIT ★ 1 -
🛡️ PII redaction for Claude, powered by Microsoft Presidio — automatic in Claude Code, on-demand in Claude Desktop.
MIT -
@mukundakatta/pii-sentry-mcpgithub.com/mukundakatta/pii-sentry-mcpupdated this year
MCP server exposing pii-sentry: detect and redact PII (emails, phones, SSNs, credit cards, API keys) from text before AI processing. Built for Claude Desktop, Cursor, Cline, Windsurf, and Zed.
npm MIT -
Redact PII and PHI from your AI agents with Philter, over the Model Context Protocol.
Apache-2.0 ★ 2 -
MCP server for local PII scanning and redaction. Check sensitive files and create redacted copies from Claude Code. Powered by DataFog Core.
pypi MIT -
Read-only, PII-redacting MCP server for the Airtable Web API
npm MIT -
@hackspaces/hubspot-connect-mcpupdated this year
Read-only, PII-redacting MCP server for the HubSpot CRM API
npm MIT -
Questa Privacy MCP — anonymize and redact PII before it reaches AI models.
NOASSERTION -
MCP server for Strac DLP — detect and redact PII, PHI, PCI and secrets before an AI agent sees them.
pypi MIT ★ 8 -
umbryn-mcpgithub.com/Rinava/umbryn-mcpupdated this year
MCP server for redacting PII/PHI and de-identifying healthcare text before it reaches an LLM. self-hosted, fail-closed, HIPAA-aware.
pypi MIT -
memory-governancegithub.com/mzyag/memory-governanceupdated this year
A governance layer for AI agent memory — access control, audit trails, retention policies, and PII redaction via MCP.
MIT -
Cover for Claude Desktop. Redact PII from PDFs locally via MCP; documents never leave your Mac.
MIT -
safety-agent-mcpupdated this year
MCP server for Superagent.sh API integration - security guardrails, PII redaction, and claim verification
npm MIT -
@superagent-ai/mcpupdated this year
MCP server for Superagent.sh API integration - security guardrails, PII redaction, and claim verification
npm MIT -
agentpiergithub.com/gatewaybuddy/agentpierupdated this year
Airlock — infra-identifier + PII redaction for AI agent traces. Catches account IDs, ARNs, IPs, hostnames, bucket names, secrets AND PII in one pass. Library + MCP server. Apache-2.0.
NOASSERTION -
pii-redactor-mcpgithub.com/klyph-io/pii-redactor-mcpupdated this year
MCP server for PII Redactor — redact PII from text via AI assistants
★ 1 -
tabulusgithub.com/WalkingMountain/tabulusupdated this year
Postgres MCP server that redacts PII & secrets before your AI agent sees them. Read-only, agent-first.
pypi MIT -
@treza/mcpgithub.com/treza-labs/treza-sdkupdated this year
Model Context Protocol server for Treza Enclaves — lets AI agents manage TEEs, verify attestations, redact PII, and sign transactions
npm MIT -
MCP server: extract tables from digital PDF invoices/bank statements to CSV/JSON/Excel with PII redaction
oci MIT -
visus-mcpgithub.com/visus-mcp/visus-mcpupdated this year
Security-first MCP server. Sanitizes web content before it reaches your LLM — strips prompt injection, redacts PII, and reduces token consumption by up to 70%.
npm MIT -
Deterministic prompt injection classification, secret entropy detection, PII redacting, and synthetic dataset bias auditing.
MIT -
privacy-filter-modulegithub.com/dwain-barnes/privacy-filter-moduleupdated this year
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 logged, UK-aware (NI numbers, postcodes, phones). Data sanitisation.
★ 2 -
MCP server for AI agent security -- input validation, prompt injection detection, PII redaction, policy enforcement, rate limiting, and audit logging
cargo MIT ★ 1 -
DocuGuard-AI-Agents-Intensive-Vibe-Coding-Capstone-Projectgithub.com/shrimantasatpati/DocuGuard-AI-Agents-Intensive-Vibe-Coding-Capstone-Projectupdated this year
DocuGuard Enterprise: A Dual-MCP multi-agent pipeline using Gemini 2.5 Flash to autonomously route and redact PII and corporate secrets.
-
@expunct/mcpgithub.com/expunct/expunct-mcpupdated this year
MCP server for Expunct — PII detection and redaction tools for Claude Code, Claude Desktop, and any MCP-compatible AI client. Supports text, PDF, DOCX, images, video, and audio.
npm MIT -
Reference multi-agent banking assistant for UK retail banking: PII redaction before the LLM, MCP tool servers, customer-confirmed actions, cost and traces per turn.
-
@safekeylab/mcp-piigithub.com/safekeylab/safekeylab-mcpupdated this year
SafeKeyLab PII Detection MCP Server - Detect and redact PII in text, images, and documents
npm MIT -
Apache-2.0 Python memory engine for AI agents with provenance (user_stated/agent_inferred/third_party), PII redaction, temporal validity, BM25+vector RRF, and pre-action gating on SQLite & Postgres.
pypi Apache-2.0 ★ 18 -
injection-pii-guardrail-mcpgithub.com/ss-2303/agent-guardrail-mcpupdated this year
An MCP server providing prompt-injection detection, PII/secrets redaction, and an audit trail for AI agents.
pypi MIT -
@fairquery/agent-trust-mcpactive
Fairquery Agent Trust & Data Safety MCP server: PII/secret redaction, email validation, sanctions screening, dependency checks and a local MCP server pre-check for AI agents. Free local tools + optional paid Apify-backed deep tools.
npm MIT -
pg-redact-mcpgithub.com/sam-david/pg-redact-mcpupdated this year
A PostgreSQL MCP server that automatically detects and redacts PII in query results before they reach AI agents.
★ 4 -
MCP server that redacts secrets and PII from files before an AI coding agent (Claude Code, Cursor, Codex) ever reads them into its context — closing the agent-reads-file leak surface that chat-box privacy tools don't cover.
npm SEE LICENSE IN LICENSE -
LLM-nexusgithub.com/saanvijay/LLM-nexusupdated this year
A transparent HTTPS proxy between any AI client and upstream LLMs — redacts PII, compresses prompts, caches semantically similar responses, and surfaces everything in a real-time dashboard. Configurable via a single JSON file with upstream proxy chaining and MCP server integration.
MIT -
Four Forward Deployed Engineer tasks. An MCP server over stdio with strict validation, an MCP security gateway with role based tool filtering, a streaming PII redaction guardrail, and a token aware rate limiter with model failover on sqlite. Python, 267 tests, no network needed.
MIT -
promptguard-mcp-servergithub.com/acebot712/promptguardupdated this year
PromptGuard MCP server — scan prompts, redact PII, and audit LLM SDK usage from any MCP client
pypi MIT -
MCP server with 90 local multimedia tools — PDF, image, audio, video, Office, PII redaction
MIT ★ 1 -
Zero-Trust PII & secrets redaction MCP server for Cursor & Claude. Lightweight, zero-dependency Presidio alternative for Node.js / TypeScript.
npm NOASSERTION ★ 3 -
veladon-mcp-pii-redactorgithub.com/grindworks-studio/veladon-mcpupdated this year
MCP server that redacts PII/PHI/secrets from outbound prompts before they leave your AI agent. Deterministic, local, auditable — built for CISOs preparing for EU AI Act Article 26 (Aug 2, 2026) and ISO 42001.
npm Apache-2.0 -
Scans datasets/models for PII/secrets, redacts, and packages a public-release bundle via MCP.
pypi -
stripe-mcp-servergithub.com/udaykapur/stripe-mcp-serverupdated this year
Local MCP server for Stripe with PII redaction, Zod validation, and idempotency keys
MIT ★ 1 -
Omitly — Redaction Leak Check (free)no update data
Local, offline check for exposed or recoverable sensitive content in PDFs, plus verification of a redacted PDF. Diagnosis only — nothing is uploaded, nothing is redacted. Actual removal is the licensed Omitly desktop app. Runs entirely on-device: re-extracts a PDF's text layer (including text hidden under black-box redaction marks, superseded incremental-update revisions, metadata, and form fields) and reports anything that looks like PII — emails, SSNs, phone numbers, card numbers, and Australian identifiers (TFN/ABN/ACN/Medicare/CRN/IHI/BSB). Never redacts a file and never issues a certificate. To actually remove sensitive data with a verifiable, offline-checkable proof of removal, use the licensed Omitly desktop app: https://omitly.app Tools: check_redaction, find_sensitive_regions, locate_text, verify_redaction — all diagnosis-only, all local.
smithery -
MCP server: redact PII (emails, phones, credit cards, SSNs, IPs, secrets) from text before it leaves your control.
npm MIT -
PrivacyScrubber PII Masking MCPno update data
Zero-Trust Data Sanitization (ZTDS) MCP Server for Claude Desktop, Cursor, Windsurf, and other AI clients. Automatically intercepts and redacts PII, credentials, and sensitive corporate data locally on your machine before they are sent to external LLMs. ### 🔒 100% Local & Airplane Mode Verified All sanitization runs inside local RAM. No data ever leaves your computer, ensuring compliance with GDPR, HIPAA, SOC 2, and internal GRC policies. Zero network calls, zero server logs. ### 🛠️ Supported Formats & File Types Locally parse and sanitize: - **Documents:** `.docx` (Microsoft Word) parsed locally with Zero-Server extraction. - **Code & Configs:** `.js`, `.py`, `.go`, `.rs`, `.json`, `.yaml`, `.ini`, `.env`, and source code files. - **Data & Logs:** `.txt`, `.log`, `.csv`, `.tsv`, `.md`, and plain text outputs. ### 🏷️ Redacted Entity Types - **Personal Data:** Names (`NAME`), Emails (`EMAIL`), Phone Numbers (`PHONE`). - **Credentials:** API Keys, passwords, tokens, SSH keys, database URIs. - **Identifiers (`ID`):** SSNs, Tax IDs, credit card numbers, and custom regex patterns. ### 🎛️ 22+ Specialized Industry Detection Profiles Specify detection rules tailored to your workload (requires PRO key): - **Engineering & IT:** `Dev`, `Tech`, `Security`, `Agents` - **Corporate & Operations:** `General`, `Bizops`, `Sales`, `Support`, `Marketing`, `Creative` - **Financial & Professional:** `Finance`, `WealthMgmt`, `Insurance`, `Accounting` - **Legal & Compliance:** `Legal`, `Compliance`, `CCPA`, `HR` - **Healthcare & Research:** `Medical`, `Pharma`, `Academic` - **Personal Use:** `Personal` ### 🔧 Available Tools - `sanitize_text` — Scrub PII/Secrets locally in text context. - `reveal_text` — Reversible token mapping (Original -> Token -> Original). - `sanitize_file` — Local sanitization of raw plain text and DOCX files.
smithery -
Database MCP server for MySQL, MariaDB, PostgreSQL, and SQLite - with builtin PII redaction and write-prevention
cargo MIT ★ 33 -
guardpostgithub.com/cognis-digital/guardpostupdated this year
Runtime agent firewall — PII redaction, rate limits, policy enforcement
NOASSERTION -
Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.
pypi Apache-2.0 ★ 17 -
Built a 5-stage multi-agent workflow (Triage, Document Verification, Fraud Analysis, Decisioning, Compliance Auditing) with guardrails for input sanitization and PII redaction.
-
Zero-trust privacy layer, streaming PII redaction gateway & FastMCP server for AI coding agents
pypi MIT ★ 2 -
Content moderation with prompt injection detection, toxicity scoring, and PII redaction
npm MIT -
MCP server exposing CerbereAG runtime security checks (prompt injection, PII redaction, tool authorization) to any MCP-compatible AI agent (Claude, Cursor, Cline, custom agents).
pypi MIT -
KBMesh — Secure AI Knowledge Base Mesh. On-premise, AI-native KB with multi-channel ingestion, GraphRAG, MCP gateway, and egress-only PII redaction.
NOASSERTION -
Cross-platform Swift-based MCP server providing comprehensive text processing, content analysis, and Apple ecosystem integration. Features 21 professional tools including PII redaction, summarization, intent analysis, Shortcuts execution, and Voice Control with enterprise-grade security.
MIT ★ 4 -
AgentCloakgithub.com/ryanfren/AgentCloakupdated this year
Secure email proxy for AI agents — content filtering, PII redaction, and prompt injection detection over MCP
NOASSERTION ★ 14 -
zero-ai-gatewaygithub.com/vishtechie07/zero-ai-gatewayupdated this year
Zero-Trust AI Gateway: Dual-pass PII redaction (Regex + LLM), real-time security monitoring with Kafka/WebSockets, and MCP-powered compliance auditing for enterprise AI safety.
MIT -
bedrock-ops-mcpgithub.com/MukundaKatta/bedrock-ops-mcpupdated this year
MCP server: AWS Bedrock model capability lookup, feature pre-check, and PII-safe response redaction. Wraps bedrock-ops.
npm Apache-2.0