Криптографический журнал аудита для ИИ-агентов через протокол Model Context Protocol
Related MCP server: DCL Evaluator
PiQrypt MCP Server предоставляет доступ по протоколу Model Context Protocol к PiQrypt — постквантовому криптографическому журналу аудита для ИИ-агентов.
Варианты использования:
🤖 ИИ-агенты: подпись каждого решения криптографическим доказательством
📊 Рабочие процессы n8n: добавление журнала аудита в процессы автоматизации
🏦 Торговые боты: соответствие требованиям SEC/FINRA для автоматизированной торговли
👥 HR-автоматизация: принятие решений о найме с помощью ИИ в соответствии с GDPR
🏥 ИИ в здравоохранении: журнал аудита HIPAA для медицинских решений
1. Установите piqrypt (обязательно — Python 3.8+)
pip install piqryptMCP-сервер делегирует все криптографические операции Python-пакету piqrypt.
Если он не установлен, сервер будет возвращать понятную ошибку при каждом вызове инструмента.
2. Установите MCP-сервер (Node.js 18+)
npm install -g @piqrypt/mcp-servernpx @piqrypt/mcp-servergit clone https://github.com/piqrypt/piqrypt-mcp-server
cd piqrypt-mcp-server
npm install
npm run buildПо умолчанию сервер использует python3 (Linux/Mac) или python (Windows).
Если piqrypt установлен в виртуальном окружении, установите эту переменную, чтобы указать путь к нужному интерпретатору:
Windows
set PIQRYPT_PYTHON=C:\path\to\venv\Scripts\python.exeLinux / Mac
export PIQRYPT_PYTHON=/path/to/venv/bin/pythonЧтобы сделать настройку постоянной, добавьте её в конфигурацию вашего MCP-клиента:
{
"mcpServers": {
"piqrypt": {
"command": "piqrypt-mcp-server",
"args": [],
"env": {
"PIQRYPT_PYTHON": "/path/to/venv/bin/python"
}
}
}
}Добавьте в ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"piqrypt": {
"command": "piqrypt-mcp-server",
"args": []
}
}
}Установите интеграцию n8n MCP
Добавьте PiQrypt MCP-сервер в конфигурацию
Используйте в рабочих процессах через узел MCP
Клиент | Версия | Примечания |
Любой MCP-совместимый клиент | Спецификация MCP 2024-11+ | транспорт stdio |
n8n | 1.88+ | через узел MCP |
Cursor | любой | добавить в настройки mcp |
VS Code | любой | добавить в настройки mcp |
Continue | любой | добавить в настройки mcp |
Windsurf | любой | добавить в настройки mcp |
Платформа | Интеграция | Вариант использования |
n8n | Узел MCP (нативный) | Журнал аудита без кода |
Make.com | Модуль HTTP | Фиксация событий через вебхуки |
Zapier | Вебхуки + HTTP | Базовая запись событий |
Каждый вызов инструмента проходит через 4 операции — фиксация (stamp), проверка (verify), экспорт (export), поиск (search). Вот что это означает на практике в зависимости от вашего контекста:
Автоматизированная торговля / финансы Любой агент, который отправляет ордера, ребалансирует портфели или инициирует транзакции, может зафиксировать каждое решение перед исполнением. Подписанная цепочка может быть экспортирована для аудита SEC/FINRA без дополнительной инфраструктуры.
HR и автоматизация найма Любой рабочий процесс, который оценивает кандидатов, выставляет баллы за резюме или распределяет соискателей, может зафиксировать каждое решение. Обеспечивает журнал аудита, соответствующий ст. 22 GDPR для найма с помощью ИИ — кто решил что, когда и какие данные использовались (хешированные, никогда не хранятся в сыром виде).
Контент и издательские процессы Любой агент, который составляет черновики, одобряет или публикует контент, может зафиксировать каждый шаг. Полезно, когда несколько ИИ-агентов сотрудничают, и вам нужно доказать авторство — какой агент что написал и в каком порядке.
DevOps и CI/CD Любой агент, который инициирует развертывание, объединяет ветки или меняет секреты, может зафиксировать каждое действие. Обеспечивает защищенную от несанкционированного доступа запись об изменениях инфраструктуры, сделанных автономными агентами.
Здравоохранение и медицинский ИИ Любой диагностический или сортировочный агент может зафиксировать каждую рекомендацию. Обеспечивает журнал аудита, соответствующий HIPAA, связывающий каждый результат ИИ с проверяемой личностью агента.
Общий шаблон во всех случаях:
[Agent makes decision]
↓
piqrypt_stamp_event ← sign + chain
↓
[Agent executes action]
↓
piqrypt_export_audit ← portable proof, verifiable
without PiQrypt installedpiqrypt_stamp_eventПодписать решение ИИ криптографическим доказательством.
Параметры:
agent_id (строка, обязательно): Идентификатор агента
payload (объект, обязательно): Данные решения
previous_hash (строка, опционально): Хеш предыдущего события для создания цепочки
Пример:
const event = await mcp.call('piqrypt_stamp_event', {
agent_id: 'trading_bot_v1',
payload: {
action: 'buy',
symbol: 'AAPL',
quantity: 100,
price: 150.25
}
});Возвращает:
{
"version": "AISS-1.0",
"agent_id": "trading_bot_v1",
"timestamp": 1739382400,
"nonce": "uuid-...",
"payload": { ... },
"previous_hash": "sha256:...",
"signature": "base64:..."
}piqrypt_verify_chainПроверить целостность цепочки событий.
Параметры:
events (массив, обязательно): События для проверки
Пример:
const result = await mcp.call('piqrypt_verify_chain', {
events: [event1, event2, event3]
});Возвращает:
{
"valid": true,
"events_count": 3,
"chain_hash": "sha256:...",
"errors": []
}piqrypt_export_auditЭкспортировать журнал аудита для соответствия требованиям.
Параметры:
agent_id (строка, обязательно): Агент для экспорта
certified (логическое): Запросить сертификацию PiQrypt
output_format (строка): json или pqz
Пример:
const audit = await mcp.call('piqrypt_export_audit', {
agent_id: 'trading_bot_v1',
certified: true,
output_format: 'json'
});piqrypt_search_eventsБыстрый поиск через индекс SQLite.
Параметры:
event_type (строка, опционально): Фильтр по типу
from_timestamp (число, опционально): Время начала
to_timestamp (число, опционально): Время окончания
limit (число): Макс. количество результатов (по умолчанию: 100)
Пример:
const trades = await mcp.call('piqrypt_search_events', {
event_type: 'trade_executed',
from_timestamp: 1739300000,
limit: 50
});Каждое зафиксированное событие отображается в Vigil — локальной панели мониторинга PiQrypt.
Примечание: Vigil не запускается автоматически MCP-сервером. Вы должны запустить его отдельно перед открытием панели.
piqrypt vigil
# → http://localhost:8421Бесплатный уровень включает: состояние цепочки, показатель риска VRS, историю за 7 дней, КРИТИЧЕСКИЕ оповещения. Перейдите на Pro для получения истории за 90 дней, управления TrustGate и постквантовых подписей.
Агенты создаются автоматически при первой фиксации. Чтобы просмотреть и удалить агентов:
Запустите Vigil: piqrypt vigil
Откройте http://localhost:8421
Перейдите в представление All Agents
Отметьте агентов для удаления → нажмите ✕ Delete selected
Подтвердите — Vigil вернется на экран приветствия, когда агентов не останется
Агенты хранятся в
~/.piqrypt/agents/на вашем компьютере. Удаление агента навсегда удаляет его ключи и историю событий.
┌─────────────────────────────────────┐
│ MCP Client (any MCP-compatible client) │
│ ↓ JSON-RPC over stdio │
├─────────────────────────────────────┤
│ MCP Server (TypeScript/Node.js) │ ← No crypto here
│ ↓ subprocess call │
├─────────────────────────────────────┤
│ Python Bridge (bridge.py) │
│ ↓ invokes CLI │
├─────────────────────────────────────┤
│ PiQrypt CLI (Python) │
│ ↓ uses │
├─────────────────────────────────────┤
│ Core Crypto (aiss package) │ ← All crypto here
│ • Ed25519 / Dilithium3 │
│ • RFC 8785 canonical JSON │
│ • Hash chains │
└─────────────────────────────────────┘✅ Приватные ключи никогда не передаются на уровень MCP ✅ Вся криптография на Python (Ed25519, Dilithium3) ✅ Такая же безопасность, как у CLI (изоляция процессов) ✅ Соответствие RFC AISS-1.1 (идентичный вывод) ✅ Валидация входных данных перед вызовом подпроцесса
[Webhook: price alert]
↓
[AI Decision: buy/sell?]
↓
[PiQrypt MCP: stamp decision] ← Audit trail
↓
[Execute trade API]
↓
[Database: store proof][Upload CV]
↓
[AI Agent: evaluate candidate]
↓
[PiQrypt MCP: stamp evaluation] ← GDPR compliance
↓
[Email HR team]# Build
npm run build
# Test bridge
python3 src/python/bridge.py stamp '{"agent_id":"test","payload":{"action":"test"}}'
# Test MCP server (manual)
node dist/index.js
# Then send MCP request via stdinError: piqrypt is not installed in this Python environmentИнтерпретатор Python, используемый MCP-сервером, не может найти пакет piqrypt.
Решение:
pip install piqryptЕсли piqrypt установлен в виртуальном окружении, а не в системном Python, установите PIQRYPT_PYTHON для указания правильного интерпретатора:
# Linux / Mac
export PIQRYPT_PYTHON=/path/to/venv/bin/python
# Windows
set PIQRYPT_PYTHON=C:\path\to\venv\Scripts\python.exeЧтобы проверить, какой Python будет использовать сервер:
# Linux / Mac
$PIQRYPT_PYTHON -c "import aiss; print('ok')"
# Windows
%PIQRYPT_PYTHON% -c "import aiss; print('ok')"Мы приветствуем вклад! См. CONTRIBUTING.md.
MCP Server → Лицензия MIT - см. LICENSE PiQrypt Core → бесплатный уровень + коммерческие уровни
PiQrypt Core: https://github.com/piqrypt/piqrypt
Протокол MCP: https://modelcontextprotocol.io
n8n: https://n8n.io
Документация: https://docs.piqrypt.com
Создано с ❤️ компанией PiQrypt Inc.
Export the complete agent audit trail to a portable JSON archive. Set certified=true to request a PiQrypt CA signature for legal admissibility (eIDAS Art.26). The export is self-contained and verifiable without PiQrypt installed.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | Agent ID to export | |
| certified | No | Create certified export (requires Pro license) | |
| output_format | No | Output format (json or encrypted pqz archive) | json |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that export is self-contained and verifiable, and mentions Pro license requirement. Does not detail side effects or reading behavior; with no annotations, this is moderate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, each adding essential information: purpose and certification detail. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Lacks output schema but describes the result as a portable JSON archive. Missing details on error conditions or what the audit trail contains, but adequate for a simple export.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. Description adds value for the certified parameter (legal admissibility) and clarifies the export scope (complete trail).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool exports a complete agent audit trail to JSON, using a specific verb and resource. It distinguishes well from sibling tools like piqrypt_search_events.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context on when to use certified=true and notes the export is self-contained. Lacks explicit when-not-to-use or alternatives, but siblings are distinct actions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the agent's cryptographic event history by type, time range, or session. Returns signed events with chain metadata. Use to reconstruct what an agent did during a specific period.
| Name | Required | Description | Default |
|---|---|---|---|
| event_type | No | Filter by event type (e.g., "trade_executed", "decision_made") | |
| from_timestamp | No | Start timestamp (Unix UTC seconds) | |
| to_timestamp | No | End timestamp (Unix UTC seconds) | |
| limit | No | Maximum number of results |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description states it returns signed events with chain metadata, implying read-only. However, it does not mention authentication, rate limits, pagination behavior, or what happens with empty results.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences with no filler. The action verb is front-loaded, and every sentence adds useful context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema; description gives a brief idea of return values (signed events with chain metadata) but omits details like event structure or metadata fields. The mention of session without a corresponding parameter reduces completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the description adds minimal value beyond repeating filter options. It mentions session but the schema lacks a session parameter, creating slight ambiguity.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb (search), resource (cryptographic event history), and scope (by type, time range, or session). Distinguishes from siblings like piqrypt_stamp_event (create) and piqrypt_export_audit (export).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides a clear use case ('reconstruct what an agent did during a specific period'), but does not explicitly state when not to use or mention alternatives among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a tamper-proof cryptographic record of an agent decision. Signs the event with Ed25519, links it to the previous event in a hash chain (AISS v2.0). Call this after every significant agent action. Required for GDPR Art.22, EU AI Act Art.13, HIPAA audit trail, SEC/FINRA trading compliance.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | Agent identifier (e.g., "trading_bot_v1", "hr_decision_engine") | |
| payload | Yes | Event payload containing decision data (JSON object) | |
| previous_hash | No | Optional hash of previous event for chain integrity |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description discloses key behaviors: tamper-proof record creation, Ed25519 signing, and hash chain linking. It lacks details on side effects, idempotency, or error handling, but covers essential traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at two sentences, front-loading the purpose and including key details. It is efficient but could be slightly more structured by grouping regulations separately.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 3 parameters and no output schema, the description covers purpose, usage, and behavioral details adequately. The lack of return value description is a minor shortfall, but overall it is fairly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes all three parameters with 100% coverage. The description adds no additional semantics beyond the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool creates a cryptographic record, specifying the signing algorithm (Ed25519) and chaining mechanism (AISS v2.0), which distinguishes it from sibling tools for export, search, and verification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly advises 'Call this after every significant agent action' and lists regulatory requirements, providing strong contextual cues. However, it does not explicitly exclude cases where the tool should not be called.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify that an agent's decision history is intact and untampered. Detects modified events, missing events, hash chain breaks, and forks. Call before trusting any historical agent output.
| Name | Required | Description | Default |
|---|---|---|---|
| events | Yes | Array of PiQrypt events to verify |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description adequately describes what the tool detects (tampering evidence). However, it lacks details on output/return behavior (e.g., error vs result) and side effects, which would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no wasted words, front-loaded with the main action and key details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with full schema coverage, the description covers purpose and usage. It lacks specification of return value (e.g., boolean, report), but overall is complete enough for an agent to invoke correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the description does not add additional meaning beyond the schema's 'Array of PiQrypt events to verify'. Baseline score of 3 is appropriate as the schema already carries the parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: verifying integrity of an agent's decision history. It lists specific detection capabilities (modified events, missing events, etc.) and distinguishes itself from siblings by its verification role.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes explicit usage guidance: 'Call before trusting any historical agent output.' While it doesn't explicitly exclude scenarios or name alternatives, the clear context is sufficient for an agent to decide when to invoke this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.5.3piqrypt_export_auditpiqrypt_search_eventspiqrypt_stamp_eventpiqrypt_verify_chainEach tool has a distinct purpose: export, search, stamp, and verify. No overlap, clear boundaries.
All tools follow the consistent pattern 'piqrypt_verb_noun' (export_audit, search_events, stamp_event, verify_chain). Perfect uniformity.
Four tools cover the essential operations for a cryptographic audit trail server without redundancy or deficiency.
The set provides a complete workflow: create events (stamp), search them, export them, and verify integrity. No obvious gaps for the domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Register every AI agent, log every action, prove it. EU AI Act compliance built in.
Bitcoin-anchored, tamper-evident audit-permanence layer for AI agents, FRE 902(13)/(14)-shaped.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PiQrypt/piqrypt-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server