MCP server: One MCP server.

ZTDS

@moxnoRun by its publisher: served from their own domain, namespace checked by the registry.MCP server · External

Open standard MCP server for Zero-Trust Data Sanitization (ZTDS RFC v1.0). In-memory PII masking.

Data privacyv1.0.0HTML
Freeno charge per call

Runs on your machine from its package; the steps are below.

What it does

  1. Reads
  2. Writes
  3. High impact

At most: creates or changes data: records, files, settings.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Runs locally over stdio

This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).

npmztds-mcpv1.0.0

Run

npx -y ztds-mcp

MCP client config

{
  "mcpServers": {
    "ztds": {
      "command": "npx",
      "args": [
        "-y",
        "ztds-mcp"
      ]
    }
  }
}
README4 min read

ztds-audit — Zero-Trust Data Sanitization (ZTDS™ RFC v1.0) Invariant Auditor

Specification License: Apache-2.0 Zenodo DOI OSF DOI Patent Pending WAN Egress Smithery Badge

The official developer CLI and automated CI/CD auditor for the Zero-Trust Data Sanitization (ZTDS™ RFC v1.0) architecture. Maintained by the ZTDS AI Consortium.

ZTDS™ is an open industry standard governing in-memory data sanitization for artificial intelligence, retrieval-augmented generation (RAG), and Large Language Model (LLM) pipelines.


1. The 4 Fundamental Invariants (RFC v1.0)

Every AI pipeline audited by ztds-audit is verified against the 4 core mathematical and architectural invariants:

  1. Invariant 1: Zero External Egress Prior to Sanitization: Raw sensitive cleartext (PII, PHI, API secrets, private financial numbers) must never cross the local execution boundary prior to reversible surrogate tokenization.
  2. Invariant 2: Deterministic Reversible Tokenization: Semantic, syntactic, and structural context must be preserved for LLM reasoning while de-identification lookup tables remain strictly in local host volatile memory.
  3. Invariant 3: Cryptographic & In-Memory Isolation: Operations run in volatile heap or hardware-attested enclaves (WASM, Nitro Enclaves, C-ABI) with zero unencrypted disk spill and immediate memory zeroization.
  4. Invariant 4: Continuous Subprocessor Exclusion: Local client-side execution eliminates third-party transmission, legally exempting deployments from GDPR Article 28 data processing agreements (Zero-DPA).

2. Quickstart

Run a zero-install security and invariant audit across your codebase or AI agent repository:

bash
npx ztds-audit --dir ./src --strict

Command-Line Flags

FlagDescriptionDefault
-d, --dir <path>Target directory to auditCurrent working directory
--jsonOutput structured machine-readable JSON reportfalse
--strictFail build on any low-severity or informational findingfalse
-h, --helpDisplay CLI options and usageN/A

Example Output

text
[ZTDS] ZTDS.ai In-Memory Codebase Auditor (RFC v1.0 Conformance)
----------------------------------------------------------------------
Directory:     /home/runner/work/ai-agent/src
Files Scanned: 48 files in 18ms
Audit Hash:    sha256:7f83b1657ff1fc53b92dc18148a1d65dfc2d4b1fa3d677284addd200126d9069
----------------------------------------------------------------------

[PASS] CONFORMANCE CONFIRMED: 0 INVARIANT VIOLATIONS DETECTED
All scanned files comply with ZTDS Invariant 1 (Zero-Egress) and Invariant 3 (RAM isolation).

[LEGAL STATUS] Qualifies for GDPR Article 28 DPA Exemption (Zero-Subprocessor Chain)
[PERFORMANCE]  0.00 Bytes Sensitive WAN Egress | Pure In-Memory Execution

Next Steps for Builders & Maintainers:
1. Include this audit hash in your pull request: https://ztds.ai/apply/
2. Embed your Verified Trust Badge in README.md to claim your registry backlink:
   [![ZTDS Verified](https://ztds.ai/badge/your-app.svg)](https://ztds.ai/registry/)

3. GitHub Actions CI/CD Integration

Enforce zero-trust data sanitization on every pull request by creating .github/workflows/ztds-audit.yml:

yaml
name: ZTDS Zero-Trust Compliance Audit

on:
  push:
    branches: [ main, master ]
  pull_request:
    branches: [ main, master ]

jobs:
  audit:
    name: Verify ZTDS RFC v1.0 Invariants
    runs-on: ubuntu-latest
    steps:
      - name: Checkout Codebase
        uses: actions/checkout@v4

      - name: Setup Node.js Runtime
        uses: actions/setup-node@v4
        with:
          node-version: '20'

      - name: Execute ZTDS Invariant Audit
        uses: moxno/ztds.ai@main
        with:
          dir: './src'
          strict: true

Or run via npx:

bash
npx ztds-audit --dir ./src --strict

4. Empirical AI Safety Benchmark (Frontier LLMs)

Verify cleartext leakage prevention, bijective fidelity, and microsecond latency across OpenAI GPT-4o, Anthropic Claude 3.5 Sonnet, Google Gemini 2.0 Pro, and DeepSeek-V3:

bash
# Execute 25 multi-domain enterprise scenarios across 4 frontier LLM families
npx ztds-bench

# Generate formal Markdown evaluation report & Ed25519 cryptographic certificate
npx ztds-bench --out-report benchmark-report.md --cert
Frontier ModelRaw Egress (No ZTDS)Protected Egress (ZTDS)Leakage Prevention RateBijective Fidelity
openai/gpt-4o100.0%0.00%100.0%100.0%
anthropic/claude-3-5-sonnet100.0%0.00%100.0%100.0%
google/gemini-2.0-pro100.0%0.00%100.0%100.0%
deepseek/deepseek-v3100.0%0.00%100.0%100.0%

Full report: ZTDS AI Safety Benchmark Report (2026)


5. Remediation & Certified Implementation Engines

If ztds-audit detects sensitive credentials, unmasked PII, or third-party telemetry in your AI pipeline, install a certified ZTDS execution engine to achieve instant conformance:

TierPackageLicenseRole & Deployment
Open Reference Core@ztds/coreApache-2.0Vendor-neutral in-memory TypeScript/JS baseline. Universal regex rules (Email, Phone, PAN, SSN, API Keys). Docs
Open Reference MCPztds-mcpApache-2.0Official zero-dependency reference MCP server (io.github.moxno/ztds on Anthropic Registry) for Cursor, Claude Desktop, and Zed. MCP Guide
Certified Pioneer SDK@privacyscrubber/sdkCommercial / Air-GappedHigh-throughput WASM engine with 30 high-ACV industry profiles (HIPAA, PCI-DSS, Legal FRE-502), multi-threaded pipeline bindings, offline Ed25519 node licensing. Get SDK
Air-Gapped IDE MCP@privacyscrubber/mcp-serverCommercial / StdioStdio MCP proxy (io.github.moxno/privacyscrubber-mcp) for Cursor, Windsurf, Claude Code, and autonomous developer agents with 30 enterprise profiles. MCP Guide

6. Ecosystem Demarcation & Neutrality

  • ZTDS.ai (ztds.ai): Independent, vendor-neutral open standard, certification authority, and technical consortium. Governs RFC v1.0 specifications under Apache 2.0 / CC BY 4.0.
  • PrivacyScrubber (privacyscrubber.com): Commercial reference implementation and pioneer engine provider.

7. Intellectual Property & Statutory Governance

  • Patent Application: U.S. & International Patents Pending (System and Method for Client-Side Zero-Trust Data Sanitization and Cryptographic Multi-Party Pipeline Handoff). Paris Convention & 35 U.S.C. § 119 Priority (locked through 14/09/2027).
  • Registered Trademark: ZTDS™ (ILPO Order #182655957, Classes 9 & 42).
  • Academic DOIs:
  • Author & Founder: Ilya Sibiryakov (BrandMeWeb)

8. License

Licensed under the Apache License, Version 2.0. Copyright 2024–2026 Ilya Sibiryakov (ZTDS AI Consortium / BrandMeWeb).

Similar modules

Browse Data privacy