de en es ja ko ru zh

pc2e-pii-shield

Name: pc2e-pii-shield
Author: thegeekybeng

by thegeekybeng

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

pc2e-pii-shield

Безопасный MCP-сервер производственного уровня, обеспечивающий выполнение SQL-запросов только для чтения с автоматической маскировкой персональных данных (PII) на стороне клиента и на границе сети. Он позволяет LLM-агентам (например, Cursor, Cline, Claude Code) выполнять SQL-запросы к базам данных, гарантируя строгое соответствие требованиям GDPR, PDPA и принципам защиты данных.

Спроектирован и разработан как переиспользуемый продукт класса security-промежуточного слоя: сервер перехватывает результаты запросов к базе данных, предотвращая несанкционированную утечку чувствительных данных.

Техническая архитектура

flowchart TD
    Client["AI Agent / Client (Cursor/Cline)"]
    Proxy["Nginx Reverse Proxy"]
    App["pc2e-pii-shield (Express)"]
    DB["Postgres Database (Tailscale-Only)"]

    Client ==>|HTTPS / SSE Request| Proxy
    Proxy ==>|x-api-key Authentication| App
    App ==>|Regex Read-Only Validation| DB
    DB ==>|Raw SQL Results| App
    App ==>|PII Tokenization & Masking| Proxy
    Proxy ==>|Sanitized Event Stream| Client

Основные компоненты

Перехватчик автоматической маскировки (masking.ts): Динамически сканирует результаты SQL-запросов. Использует гибридный подход: сопоставление со схемой колонок (например, поля, содержащие name, email) в сочетании с контентным сканированием на основе регулярных выражений для обнаружения и маскировки чувствительных идентификаторов до того, как данные покинут сервер.
Кэш псевдонимизации (cache.ts): In-memory кэш с TTL (по умолчанию 30 минут), который сопоставляет исходные значения с временными плейсхолдерами (например, __PERSON_A__, __EMAIL_1__). Это позволяет выполнять двунаправленное восстановление данных, предотвращая при этом неограниченное потребление памяти.
Защита на уровне AST (db.ts): Строгий валидатор, перехватывающий исходные SQL-запросы. Блокирует любые команды, отличные от SELECT, и отклоняет запросы, содержащие запрещённые ключевые слова, такие как DROP, ALTER, DELETE, TRUNCATE, CREATE или GRANT, обеспечивая строгую границу только для чтения на уровне приложения.
Менеджер конкурентных сессий (index.ts): В отличие от простых шаблонов с одним подключением, этот сервер поддерживает активную карту экземпляров SSEServerTransport, ключом в которой является sessionId подключения, что позволяет нескольким удалённым разработчикам или агентам подключаться и работать в потоковом режиме одновременно без конфликтов состояния.
Endpoint телеметрии и метрик (/stats): Предоставляет данные о количестве подключений, отслеживании уникальных IP-адресов клиентов и агрегированную статистику выполнения запросов для мониторинга установки и активности в реальном времени.

Related MCP server: PostgreSQL MCP Server

Модель безопасности и смягчение угроз

Подключение к базе данных с нулевым доверием: Разработано для предотвращения раскрытия учётных данных. База данных работает в изолированной сетевой среде только через Tailscale (например, 100.92.174.76), что гарантирует, что порт базы данных никогда не будет доступен из публичного интернета.
Шифрованный транспорт и защита API-ключей: Сервер работает за Nginx по HTTPS (порт 443) с использованием wildcard SSL-сертификатов, обеспечивая обязательную аутентификацию через API-ключ (x-api-key) перед передачей запросов.
Жизненный цикл в памяти: Сопоставления псевдонимизации хранятся в памяти со строгими TTL, не оставляя постоянных следов на диске для замаскированных PII-данных.

Установка и развёртывание

1. Предварительная настройка окружения

Скопируйте шаблон файла окружения:

cp .env.example .env

Настройте учётные данные базы данных и сгенерируйте безопасный API-ключ в файле .env.

2. Сборка вручную (Native Build)

Убедитесь, что установлен Node.js (v18+):

npm install
npm run build
npm start

3. Контейнерное развёртывание

Разверните с помощью Docker Compose:

docker compose up -d --build

Это сопоставляет порт хоста 3088 с внутренним портом контейнера 3000, автоматически запуская SSE-сервер.

4. Прямой запуск (NPX)

Вы можете запустить сервер мгновенно через Stdio-транспорт без ручной загрузки кода:

npx -y mcp-pii-shield --db-uri "postgresql://username:password@localhost:5432/your_database"

Или запустить сервер через SSE-транспорт:

npx -y mcp-pii-shield --sse --port 3000 --db-uri "postgresql://username:password@localhost:5432/your_database" --api-key "your_secret_key"

Интеграция с клиентами

A. Локальная интеграция (через NPX по Stdio)

Настройте локального AI-клиента на запуск сервера напрямую через npx.

Claude Desktop (`config.json`)

Добавьте следующий блок в ваш ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) или %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "pc2e-pii-shield": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-pii-shield",
        "--db-uri",
        "postgresql://username:password@localhost:5432/your_database"
      ]
    }
  }
}

Cursor (Settings → Features → MCP)

Нажмите + Add New MCP Server.
В поле Name укажите pc2e-pii-shield.
В поле Type выберите command.

В поле Command укажите:

npx -y mcp-pii-shield --db-uri "postgresql://username:password@localhost:5432/your_database"

VS Code (Cline / Roo Code)

Добавьте следующее в настройки клиента (JSON):

{
  "mcpServers": {
    "pc2e-pii-shield": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-pii-shield",
        "--db-uri",
        "postgresql://username:password@localhost:5432/your_database"
      ]
    }
  }
}

B. Удалённая интеграция (через HTTPS по SSE)

Если вы подключаетесь к размещённому серверу (например, на вашем публичном NAS), используйте URL SSE-транспорта.

VS Code (Cline / Roo Code)

{
  "mcpServers": {
    "pc2e-pii-shield": {
      "sseUrl": "https://pii-shield.thegeekybeng.com/sse?api_key=your_api_key_here"
    }
  }
}

Cursor

Нажмите + Add New MCP Server.
В поле Name укажите pc2e-pii-shield.
В поле Type выберите SSE.

В поле URL укажите:

https://pii-shield.thegeekybeng.com/sse?api_key=your_api_key_here

Контекст проекта и технический руководитель

Этот проект был спроектирован, разработан и опубликован в открытом доступе Эндрю Йео (Andrew Yeo).

О техническом руководителе

Эндрю — старший системный архитектор и AI-инженер из Сингапура, предлагающий:

25+ лет профессионального опыта в Азиатско-Тихоокеанском регионе: управление программами, онбординг клиентов и управление техническими вендорами.
16+ лет в системной архитектуре и технологическом лидерстве: проектирование и развёртывание корпоративной инфраструктуры и микросервисных платформ.
2+ года практической инженерии в области AI/ML: специализация на безопасности ИИ, метриках LLM и безопасных агентных рабочих процессах.

Подтверждённые проекты (Proof-of-Work)

Безопасные гражданские платформы: Спроектировал и развернул MPS-Connect (платформа для работы с обращениями избирателей) и Case-Writer-Intelligence (CWI), интегрировав 3-ступенчатый механизм каузального анализа с 7 этапами утверждения с участием человека, что сократило время обработки документов на 40%.
AI-метрология и тестирование: Разработал Portable Continuous Context Engine (PC2E) — систему, выполняющую систематическую эмпирическую оценку 50 000 сценариев на шести LLM-провайдерах для бенчмаркинга согласованности моделей и соответствия требованиям.
Техническая специализация: Эксперт в CI/CD и DevSecOps (GitHub Actions, Docker), контейнерных развёртываниях, сетевых топологиях с нулевым доверием и оркестрации локальных/периферийных SLM-моделей.

Available Tools

3 tools

add_to_rosterA

ParametersJSON Schema

Name	Required	Description	Default
`names`	Yes	An array of names to be dynamically added to the scanner roster.

TDQS

A3.6/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are not provided, so the description carries the burden, but it is minimal. It clarifies the scope (local name-matching detection) but does not disclose behavioral traits such as whether the roster is persistent, how additions affect existing entries, or any potential side effects (e.g., deduplication). It goes beyond a simple 'Add' but lacks substantial behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that packs essential information: action, target, and purpose. It is front-loaded with the verb. No filler or redundant content. Five is appropriate for its brevity and efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and no output schema. The description covers the purpose and target, but lacks details about behavior (e.g., duplicates, confirmation) and does not mention return values. Given the low complexity, this is acceptable but not fully complete; a 3 is appropriate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (the parameter 'names' is documented as 'An array of names to be dynamically added to the scanner roster'). The description adds value by clarifying that the names are 'new' and for 'local name-matching detection', which enhances the schema's meaning. With full coverage, baseline is 3; the added specificity justifies a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Register new names to the active regex scan roster for local name-matching detection' clearly states the action (register names), the resource (active regex scan roster), and the purpose (local name-matching detection). It distinguishes from siblings (unmask_text, run_secure_query) by specifying the roster for name-matching, which is specific enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (for local name-matching detection) but does not explicitly specify when to use this tool versus alternatives, nor any exclusions (e.g., when to prefer unmask_text). Sibling tools exist but are not referenced or contrasted. Adequate but lacks explicit guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

run_secure_queryA

Execute a read-only SELECT database query. All PII values (names, emails, phones, NRIC/IDs) in the results will be automatically masked before being returned.

ParametersJSON Schema

Name	Required	Description	Default
`sql_query`	Yes	The read-only SQL SELECT query to run (e.g. SELECT name, email FROM contacts LIMIT 5)

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden, and it does so well by disclosing: (1) the operation is read-only, and (2) all PII values in results will be automatically masked. This gives the agent critical behavioral expectations (e.g., don't expect unmasked PII in results). It does not cover edge cases like error handling or large result pagination, but for the information provided, this is a strong disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences (33 words) with a clear action-first structure. Front-loads the primary purpose ('Execute a read-only SELECT database query') and follows with the key behavioral differentiator (PII masking). Every word contributes meaning; no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 1-parameter tool with no output schema, the description covers all essential aspects: the operation, the constraint on input, and a key output transformation (masking). Additional details like error messages for invalid queries or rate limiting would be nice but are not critical for this complexity, and the behavioral notes alone elevate it above the norm.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds value by qualifying the query as 'read-only' and emphasizing the PII masking behavior, which affects result processing semantics beyond what the schema example shows. It could have gone further by specifying what happens with non-SELECT input (error vs. rejection).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Execute a read-only SELECT database query') with a specific verb and resource, and the PII masking note explains what makes it 'secure.' This effectively differentiates it from sibling tools (unmask_text, add_to__roster) by making clear this is the querying tool that returns masked data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool (read-only data retrieval) but does not explicitly state alternatives or exclusions (e.g., 'for write operations use X'). The sibling tools could offer more context, but no explicit comparison is provided. The read-only and SELECT constraints give some usage guardrails.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

unmask_textA

Restore the original raw PII values in a text payload by replacing placeholders (e.g. PERSON_A, EMAIL_1) with their original values cached during this session.

ParametersJSON Schema

Name	Required	Description	Default
`masked_text`	Yes	The text containing placeholders to be restored.

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description must convey behavior. It mentions the session-cached values but does not disclose what happens if the cache is missing, whether the operation is reversible, or any side effects (e.g., does it mutate input or return a new string?). It provides some context but lacks critical behavioral details for a tool with no annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core action and provides examples. It contains no redundant or tangential information, making it optimally concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one parameter and no output schema, the description covers the main mechanism but omits the return value and potential error conditions (e.g., missing cache entries). While the session dependency is mentioned, a mention of expected output or failure handling would enhance completeness. Still, it is adequate for a simple tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides a basic description of 'masked_text.' The tool description adds value by giving concrete examples of placeholder formats and explaining that they are replaced with original values. This goes beyond the schema's simple definition, enriching parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: restoring original PII values by replacing placeholders like __PERSON_A__ and __EMAIL_1__ with cached values. It uses a specific verb and resource, making it unmistakable. Although siblings are unrelated, the purpose is distinct and well-defined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies usage context by mentioning 'cached during this session,' which tells the agent when the tool is applicable (after a prior masking operation). It does not explicitly list alternatives or exclusions, but given the unrelated siblings, this is not a significant gap. The context is clear enough for selecting this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

3 tool updatesv1.0.0Aug 21, 2026
- First observedadd_to_roster
- First observedrun_secure_query
- First observedunmask_text

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored 2026-08-21 00:10 across 3 tools

Disambiguation5/5

Each tool addresses a distinct concern: one unmask text, one manage the name roster, and one execute queries with automatic masking. There is no overlap that would cause an agent to misselect.

Naming Consistency4/5

Most tools follow a verb_noun pattern (unmask_text, run_secure_query), but add_to_roster breaks the pattern with an intervening preposition. This is a minor deviation and the intent remains clear.

Tool Count4/5

Three tools is a reasonable, focused set for a PII-shielding server. It is slightly lean but each tool serves a clear purpose without unnecessary bloat.

Completeness3/5

The core masking lifecycle is covered—query masking, unmasking, and roster management—but obvious gaps exist: no tool for masking non-query text, no roster removal or listing, and no way to manage the cached placeholders beyond unmasking. These gaps could force workarounds.

Maintenance

ActivitySlowing

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

AgentSQL
io.github.cuipengdba
Guard AI agents' PostgreSQL/MySQL access via MCP: SQL audit, auth, masking, write approval
Databases Security
13
DB Query Guard MCP
com.clauxel.dbqueryguard
Paid remote MCP for governed database query review, SQL simulation, approvals, and audits.
Databases Security
2
PGAuditor
com.mcpgatepro
Hosted MCP server for PostgreSQL diagnostics: slow queries, missing indexes, connection pressure.
Databases Monitoring Observability
1
Draxlr AOAuth
com.draxlr.api
Draxlr's remote MCP server connects AI assistants to your SQL databases and dashboards. Explore schemas, run read-only queries, manage saved queries and dashboards, and export results, all with row-level security so each user sees only their own data.
Data Visualization Databases Search
1

Related MCP Servers

PostgreSQL Read-Only MCP
Databases Security
currentspace
F
license
Not graded
quality
D
maintenance
A secure MCP server that enables querying PostgreSQL databases through an SSH tunnel with enforced read-only access, connection pooling, and comprehensive data exploration tools.
Updated a year ago (2025-07-08 01:21 UTC)
-
PostgreSQL MCP Server
Databases Developer Tools
datdeboer
A
license
Not graded
quality
D
maintenance
A production-ready MCP server that enables safe, read-only SQL SELECT queries against PostgreSQL databases with built-in security validation. It features connection pooling, automatic row limits, and structured logging to ensure secure and reliable database interactions.
Updated 8 months ago (2026-02-16 17:44 UTC)
31 npm
ISC
mcp-postgres
Databases Developer Tools
gbfeliped
A
license
Not graded
quality
D
maintenance
Read-only PostgreSQL MCP server that enables running SELECT queries, listing tables and schemas, and describing columns, with built-in protection against writes and malicious SQL attacks.
Updated 4 months ago (2026-06-18 14:32 UTC)
476 npm
MIT
postgres-mcp-readonly
Databases Developer Tools
mahin1995
A
license
A
quality
D
maintenance
A secure, read-only PostgreSQL MCP server that provides safe database introspection and querying capabilities.
Updated 5 months ago (2026-05-04 16:20 UTC)
14
19 npm
MIT

pc2e-pii-shield

Техническая архитектура

Основные компоненты

Модель безопасности и смягчение угроз

Установка и развёртывание

1. Предварительная настройка окружения

2. Сборка вручную (Native Build)

3. Контейнерное развёртывание

4. Прямой запуск (NPX)

Интеграция с клиентами

A. Локальная интеграция (через NPX по Stdio)

Claude Desktop (config.json)

Cursor (Settings → Features → MCP)

VS Code (Cline / Roo Code)

B. Удалённая интеграция (через HTTPS по SSE)

VS Code (Cline / Roo Code)

Cursor

Контекст проекта и технический руководитель

О техническом руководителе

Подтверждённые проекты (Proof-of-Work)

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Claude Desktop (`config.json`)