Cryptographic audit trail for AI agents. Sign, verify, export. GDPR/HIPAA/EU AI Act.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Cryptographic Audit Trail for AI Agents via Model Context Protocol
PiQrypt MCP Server provides Model Context Protocol access to PiQrypt β the post-quantum cryptographic audit trail for AI agents.
Use cases:
1. Install piqrypt (required β Python 3.8+)
The MCP server delegates all cryptographic operations to the piqrypt Python package.
If it is not installed, the server will return a clear error on every tool call.
2. Install the MCP server (Node.js 18+)
By default the server uses python3 (Linux/Mac) or python (Windows).
If piqrypt is installed in a virtual environment, set this variable to point to the right interpreter:
Windows
Linux / Mac
To make it persistent, add it to your MCP client configuration:
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
| Client | Version | Notes |
|---|---|---|
| Any MCP-compatible client | MCP spec 2024-11+ | stdio transport |
| n8n | 1.88+ | via MCP node |
| Cursor | any | add to mcp settings |
| VS Code | any | add to mcp settings |
| Continue | any | add to mcp settings |
| Windsurf | any | add to mcp settings |
| Platform | Integration | Use case |
|---|---|---|
| n8n | MCP node (native) | No-code audit trail |
| Make.com | HTTP module | Webhook-triggered stamping |
| Zapier | Webhooks + HTTP | Basic event recording |
Every tool call goes through the same 4 operations β stamp, verify, export, search. Here is what that means in practice depending on your context:
Automated trading / finance Any agent that submits orders, rebalances portfolios, or triggers transactions can stamp each decision before execution. The signed chain is exportable for SEC/FINRA audit without any additional infrastructure.
HR and hiring automation Any workflow that evaluates candidates, scores CVs, or routes applicants can stamp each decision. Provides a GDPR Art.22 compliant audit trail for AI-assisted hiring β who decided what, when, and what data was used (hashed, never stored raw).
Content and publishing pipelines Any agent that drafts, approves, or publishes content can stamp each step. Useful when multiple AI agents collaborate and you need to prove attribution β which agent wrote what, in what order.
DevOps and CI/CD Any agent that triggers deployments, merges branches, or rotates secrets can stamp each action. Provides a tamper-evident record of infrastructure changes made by autonomous agents.
Healthcare and medical AI Any diagnostic or triage agent can stamp each recommendation. Provides a HIPAA-compliant audit trail linking each AI output to a verifiable agent identity.
The common pattern in all cases:
piqrypt_stamp_eventSign an AI decision with cryptographic proof.
Parameters:
agent_id (string, required): Agent identifierpayload (object, required): Decision dataprevious_hash (string, optional): Previous event hash for chainingExample:
Returns:
piqrypt_verify_chainVerify integrity of event chain.
Parameters:
events (array, required): Events to verifyExample:
Returns:
piqrypt_export_auditExport audit trail for compliance.
Parameters:
agent_id (string, required): Agent to exportcertified (boolean): Request PiQrypt certificationoutput_format (string): json or pqzExample:
piqrypt_search_eventsFast search via SQLite index.
Parameters:
event_type (string, optional): Filter by typefrom_timestamp (number, optional): Start timeto_timestamp (number, optional): End timelimit (number): Max results (default: 100)Example:
Every stamped event is visible in Vigil β PiQrypt's local monitoring dashboard.
Note: Vigil is not launched automatically by the MCP server. You must start it separately before opening the dashboard.
Free tier includes: chain health, VRS risk score, 7-day history, CRITICAL alerts. Upgrade to Pro for 90-day history, TrustGate governance, and post-quantum signatures.
Agents are created automatically on first stamp. To view and delete agents:
piqrypt vigilAgents are stored in
~/.piqrypt/agents/on your machine. Deleting an agent removes its keys and event history permanently.
β
Private keys never exposed to MCP layer
β
All crypto in Python (Ed25519, Dilithium3)
β
Same security as CLI (process isolation)
β
RFC AISS-1.1 compliant (identical output)
β
Input validation before subprocess call
Error: piqrypt is not installed in this Python environmentThe Python interpreter used by the MCP server cannot find the piqrypt package.
Fix:
If piqrypt is installed in a virtual environment and not the system Python, set PIQRYPT_PYTHON to point to the correct interpreter:
To verify which Python the server will use:
We welcome contributions! See CONTRIBUTING.md.
MCP Server β MIT License - see LICENSE PiQrypt Core β free tier + commercial tiers
Built with β€οΈ by PiQrypt Inc.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/audit-trail)<a href="https://allmcps.com/mcp/audit-trail"><img src="https://allmcps.com/api/badge/audit-trail?style=directory" alt="Audit Trail on AllMCPs" /></a>