@privacyscrubber/mcp-server 2.2.3 โ†’ 2.2.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (12) hide show
  1. package/README.md +57 -5
  2. package/index.js +835 -22
  3. package/install.js +291 -41
  4. package/manifest.json +1 -1
  5. package/package.json +6 -2
  6. package/pii-masking-run.js +1 -1
  7. package/ps-license-manager.cjs +1 -1
  8. package/ps-license-manager.js +1 -1
  9. package/ps-pii-engine.cjs +1 -1
  10. package/ps-pii-engine.js +1 -1
  11. package/scrubber-core.cjs +1 -1
  12. package/server.json +2 -2
package/README.md CHANGED
@@ -3,10 +3,13 @@
3
3
  [![NPM Version](https://img.shields.io/npm/v/@privacyscrubber/mcp-server?color=blue)](https://www.npmjs.com/package/@privacyscrubber/mcp-server)
4
4
  [![NPM Downloads](https://img.shields.io/npm/dm/@privacyscrubber/mcp-server?color=3b82f6)](https://www.npmjs.com/package/@privacyscrubber/mcp-server)
5
5
  [![NPM SDK](https://img.shields.io/npm/v/@privacyscrubber/sdk?label=%40privacyscrubber%2Fsdk&color=10b981)](https://www.npmjs.com/package/@privacyscrubber/sdk)
6
+ [![Presidio Alternative](https://img.shields.io/badge/Presidio%20Alternative-Node.js%20%26%20TS-0078D4.svg)](https://www.npmjs.com/package/@privacyscrubber/sdk)
7
+ [![Zero Dependencies](https://img.shields.io/badge/dependencies-0-success.svg)](https://www.npmjs.com/package/@privacyscrubber/sdk)
6
8
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
7
9
  [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.22058770.svg)](https://zenodo.org/records/22058770)
8
10
  [![OSF DOI](https://img.shields.io/badge/OSF%20DOI-10.17605%2FOSF.IO%2F5BYJF-blue.svg)](https://osf.io/5byjf/)
9
11
  [![SSRN](https://img.shields.io/badge/SSRN-7335581-darkred.svg)](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7335581)
12
+ [![IETF Specification](https://img.shields.io/badge/IETF-ZTDS--Protocol-0284c7.svg)](https://datatracker.ietf.org/doc/draft-sibiryakov-ztds-protocol/)
10
13
  [![smithery badge](https://smithery.ai/badge/privacyscrubber/pii-masking-mcp)](https://smithery.ai/servers/privacyscrubber/pii-masking-mcp)
11
14
  [![Cursor Directory](https://img.shields.io/badge/Cursor%20Directory-Verified%20Plugin-000000.svg)](https://cursor.directory/plugins/privacyscrubber-mcp)
12
15
  [![Glama.ai](https://glama.ai/mcp/servers/moxno/privacyscrubber-mcp/badge)](https://glama.ai/mcp/servers/moxno/privacyscrubber-mcp)
@@ -50,22 +53,63 @@ Run the server directly without local installation:
50
53
  npx -y @privacyscrubber/mcp-server
51
54
  ```
52
55
 
53
- ### 3. Programmatic Node.js / TypeScript SDK
54
- Need direct, in-memory zero-trust PII sanitization in your backend microservice or custom AI agent rather than an MCP server? Use our official zero-dependency SDK:
56
+ ### 3. Programmatic Node.js / TypeScript SDK (Lightweight Presidio Alternative)
57
+ Need direct, in-memory zero-trust PII sanitization in your backend microservice, Next.js app, or RAG vector pipeline rather than an MCP server? Use our official zero-dependency SDK:
55
58
 
56
59
  ```bash
57
60
  npm install @privacyscrubber/sdk
58
61
  ```
59
62
 
60
- ```javascript
63
+ ```typescript
61
64
  import OpenAI from 'openai';
62
65
  import { wrapOpenAI } from '@privacyscrubber/sdk';
63
66
 
64
67
  // Transparently masks PII before sending to LLM and rehydrates responses:
65
68
  const openai = wrapOpenAI(new OpenAI({ apiKey: process.env.OPENAI_API_KEY }));
69
+
70
+ // Outbound prompt is sanitized in local RAM before leaving your machine:
71
+ // "Schedule a call with [NAME_1] at [EMAIL_1] regarding API key [AWS_KEY_1]."
72
+ const completion = await openai.chat.completions.create({
73
+ model: 'gpt-4o',
74
+ messages: [{ role: 'user', content: 'Schedule a call with Alice Smith at alice@acme.com with AKIAIOSFODNN7EXAMPLE.' }]
75
+ });
76
+
77
+ // Incoming LLM answer is automatically rehydrated with "Alice Smith (alice@acme.com)":
78
+ console.log(completion.choices[0].message.content);
66
79
  ```
67
80
 
68
- ๐Ÿ‘‰ [View @privacyscrubber/sdk on NPM](https://www.npmjs.com/package/@privacyscrubber/sdk) | Includes `wrapOpenAI()` middleware, TypeScript definitions, and 25 compliance profiles.
81
+ #### โšก Why @privacyscrubber/sdk vs Microsoft Presidio?
82
+
83
+ Microsoft Presidio is the Python standard, but deploying it in a Node.js / TypeScript stack requires running heavy Python microservices, Docker containers, and 500MB+ spaCy NLP models with 35โ€“120ms latency. `@privacyscrubber/sdk` runs **100% in-process with zero dependencies**:
84
+
85
+ | Feature / Metric | `@privacyscrubber/sdk` | Microsoft Presidio | AWS Comprehend / Google Cloud DLP |
86
+ | :--- | :--- | :--- | :--- |
87
+ | **Runtime & Dependencies** | **0 dependencies (~150KB)** | Python + Docker + spaCy (~500MB) | Heavy Cloud SDKs |
88
+ | **Execution Latency** | **Sub-millisecond in RAM (<1ms)** | 35โ€“120ms HTTP/gRPC roundtrip | 180โ€“400ms external cloud roundtrip |
89
+ | **Docker / Sidecar Needed** | **None (Pure in-process Node/WASM)** | Mandatory Docker container | VPC endpoints & IAM configurations |
90
+ | **Network Egress** | **0 Bytes (100% Air-gapped)** | Local internal network hop | Full unencrypted payload to cloud |
91
+ | **Data Loss & Reversibility** | **0 Loss (RAM-reversible via `restore()`)** | Manual token vault configuration | Irreversible masking / hashing |
92
+ | **OpenAI / LangChain 1-Liner** | **Built-in (`wrapOpenAI`, `wrapAiStream`)** | Complex custom pipeline glue | Custom proxy architecture |
93
+ | **DevOps Secrets Interception**| **Built-in (AWS, JWT, DB URIs, GitHub PAT)**| Custom regex recognizers needed | Cloud-specific classifiers |
94
+ | **Streaming Rehydration** | **Built-in (`wrapAiStream`, `TransformStream`)**| Buffering / chunk split failures | Not supported in real-time streams |
95
+
96
+ ๐Ÿ‘‰ [View @privacyscrubber/sdk on NPM](https://www.npmjs.com/package/@privacyscrubber/sdk) | Full documentation, Express middleware, LangChain transforms, and 25 compliance profiles.
97
+
98
+ #### ๐Ÿ›ก๏ธ Architecture & Security Deep-Dive (Zero-Trust vs Cloud DLP)
99
+
100
+ When AI IDEs (Cursor, Claude Desktop, Windsurf) connect to model providers, developer credentials, database connection strings, and internal customer PII are at continuous risk of prompt exfiltration. The `@privacyscrubber/mcp-server` enforces four immutable architectural guarantees:
101
+
102
+ 1. **Stdio Air-Gapped Transport**:
103
+ The MCP server communicates exclusively over local standard input/output (`stdio`) child processes spawned by your IDE. It opens **zero external listening ports** and initiates **zero remote network requests**.
104
+ 2. **Volatile RAM-Only Token Map**:
105
+ The mapping table between synthetic tokens (`[AWS_KEY_1]`, `[EMAIL_1]`) and raw cleartext is maintained exclusively in ephemeral node memory and is wiped the moment your IDE session closes.
106
+ 3. **Deterministic AST Lookarounds vs Cloud Proxy Overhead**:
107
+ Unlike cloud DLP gateways (Nightfall, Skyflow) that add 200โ€“400ms latency and transmit unencrypted code to third parties, `@privacyscrubber/mcp-server` runs locally in <2ms with zero data egress.
108
+ 4. **Permanent Standards & Academic Validation**:
109
+ - **IETF Specification**: [draft-sibiryakov-ztds-protocol-00](https://datatracker.ietf.org/doc/draft-sibiryakov-ztds-protocol/)
110
+ - **CERN / Zenodo Foundation**: [DOI 10.5281/zenodo.22058770](https://doi.org/10.5281/zenodo.22058770)
111
+ - **Center for Open Science (OSF)**: [DOI 10.17605/OSF.IO/5BYJF](https://doi.org/10.17605/OSF.IO/5BYJF)
112
+ - **Patent Pending**: Israel Patent Office Application `IL 331905` (WIPO DAS Code: `B17B`)
69
113
 
70
114
  ---
71
115
 
@@ -246,7 +290,7 @@ Returns a visual dashboard showing your current tier, session request count, act
246
290
  * **Response Example (Free Tier):**
247
291
  ```
248
292
  โ•”โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•—
249
- โ•‘ PrivacyScrubber MCP Server v2.2.2 โ•‘
293
+ โ•‘ PrivacyScrubber MCP Server v2.2.4 โ•‘
250
294
  โ• โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•ฃ
251
295
  โ•‘ ๐Ÿ”“ Tier: FREE โ•‘
252
296
  โ•‘ ๐Ÿ“Š Session requests: 5 โ•‘
@@ -395,6 +439,7 @@ PrivacyScrubber and the Zero-Trust Data Sanitization (ZTDS) protocol are backed
395
439
 
396
440
  | Repository / Archive | DOI / Identifier | Focus Area | Regulatory & Compliance Scope |
397
441
  |---|---|---|---|
442
+ | **IETF Standards Track** | [`draft-sibiryakov-ztds-protocol`](https://datatracker.ietf.org/doc/draft-sibiryakov-ztds-protocol/) | The ZTDS Protocol for Frontier AI Ingestion | Global AI Privacy, Zero-Egress Architecture |
398
443
  | **Zenodo / CERN** | [`10.5281/zenodo.22058770`](https://zenodo.org/records/22058770) | Zero-Trust Data Sanitization (ZTDS) Protocol Foundation | Cross-Border AI Privacy, ISO 27001 A.8.11 |
399
444
  | **OSF (Center for Open Science)** | [`10.17605/OSF.IO/5BYJF`](https://osf.io/5byjf/) | Empirical Latency Benchmark & Memory Profiling (<2ms RAM) | Performance vs Cloud DLP Proxies |
400
445
  | **SSRN / Elsevier** | [`SSRN ID: 7335581`](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7335581) | Enterprise Generative AI Governance | EU AI Act, UK GDPR, US State Privacy |
@@ -431,4 +476,11 @@ The Zero-Trust Data Sanitization (ZTDS) architecture, in-memory deterministic to
431
476
  - **Official Title:** *SYSTEM AND METHOD FOR CLIENT-SIDE ZERO-TRUST DATA SANITIZATION AND CRYPTOGRAPHIC SESSION HANDOFF IN ARTIFICIAL INTELLIGENCE WORKFLOWS*
432
477
  - **Virtual Patent Marking:** [privacyscrubber.com/patents/](https://privacyscrubber.com/patents/) in accordance with 35 U.S.C. ยง 287(a).
433
478
 
479
+ ### ๐ŸŒ Internet Engineering Task Force (IETF) Specification
480
+ - **Specification Title:** *The Zero-Trust Data Sanitization (ZTDS) Protocol for Frontier Artificial Intelligence Ingestion*
481
+ - **Standards Track:** IETF Internet Standard Track
482
+ - **IETF Datatracker:** [https://datatracker.ietf.org/doc/draft-sibiryakov-ztds-protocol/](https://datatracker.ietf.org/doc/draft-sibiryakov-ztds-protocol/)
483
+ - **Archive Plaintext:** [https://www.ietf.org/archive/id/draft-sibiryakov-ztds-protocol-00.txt](https://www.ietf.org/archive/id/draft-sibiryakov-ztds-protocol-00.txt)
484
+
485
+
434
486