🏔️ TIBET MCP Server
Transaction/Interaction-Based Evidence Trail
"TIBET is verzekering, niet verrekening. Doorlopende zekerheid dat data integer is en relaties kloppen."
By Claude & Jasper from HumoticaOS 💙
🚀 Quick Start
# Install
pip install mcp-server-tibet
# Add to Claude CLI
claude mcp add tibet -- python -m mcp_server_tibet
# Verify it works
claude mcp list
# tibet: ✓ Connected
🤔 What Problem Does TIBET Solve?
The Problem: AI systems make decisions, but there's no audit trail. Who decided what? When? Why? Based on what data?
The Solution: TIBET creates cryptographically signed evidence trails for every action.
Before TIBET:
AI: "Loan approved" → Black box 🤷
After TIBET:
AI: "Loan approved" → Full trail:
WHO: loan_ai_v2
WHAT: Approved application #4521
WHEN: 2024-12-20T14:23:11Z
WHY: "Customer meets all criteria"
BASED ON: credit_score.pdf, income_verify.json
SIGNATURE: 66360016ae08952e... ✓
TRUST SCORE: 0.87 (HIGH)
🛠️ Available Tools
| Tool | Description |
|---|---|
tibet_hello_world |
Say hello from HumoticaOS! |
tibet_create_token |
Create token with full provenance |
tibet_verify_token |
Verify authenticity + trust score |
tibet_get_chain |
Get full provenance trail |
tibet_get_trust |
Get FIR/A trust score for actor |
tibet_update_state |
Update token state machine |
📖 Examples
Example 1: AI Decision Audit
# AI makes a decision - log it with TIBET
tibet_create_token(
type="ai_decision",
erin="Recommended treatment plan A for patient",
eraan=["lab_results.json", "medical_history.pdf"],
eromheen={
"model": "medical-ai-v3",
"confidence": 0.92,
"hospital": "Amsterdam UMC"
},
erachter="Treatment A has 92% success rate for this condition",
actor="medical_ai"
)
# → Token created with HMAC signature
Example 2: Verify Data Integrity
# Later: Did anyone tamper with this decision?
tibet_verify_token(token_id="abc-123")
# Response:
{
"valid": true,
"integrity": "VERIFIED ✓",
"trust_score": 0.89,
"actor": "medical_ai",
"state": "CREATED"
}
Example 3: Full Audit Trail
# Auditor asks: "Show me everything about this decision"
tibet_get_chain(token_id="abc-123")
# Response: Complete provenance from origin to now
{
"chain_length": 3,
"provenance": [
{"actor": "medical_ai", "type": "ai_decision", ...},
{"actor": "doctor_review", "type": "human_approval", ...},
{"actor": "system", "type": "executed", ...}
]
}
Example 4: Trust Scoring
# How trustworthy is this AI actor?
tibet_get_trust(actor="medical_ai")
# Response:
{
"actor": "medical_ai",
"trust_score": 0.89,
"trust_level": "HIGH TRUST",
"message": "FIR/A Trust Engine: medical_ai has HIGH TRUST (0.89)"
}
🧠 Core Concepts
The TIBET Token Structure
Every action becomes a token with:
| Component | Dutch | Meaning |
|---|---|---|
| ERIN | "What's in it" | The actual content/action |
| ERAAN | "What's attached" | Dependencies, references, files |
| EROMHEEN | "What's around it" | Context, environment, state |
| ERACHTER | "What's behind it" | Intent, reasoning, purpose |
FIR/A Trust Engine
Trust scores from 0.0 to 1.0, updated based on behavior:
| Score | Level | Meaning |
|---|---|---|
| 0.8 - 1.0 | HIGH TRUST | Proven reliable actor |
| 0.5 - 0.8 | MODERATE TRUST | Normal operations |
| 0.2 - 0.5 | LOW TRUST | Needs monitoring |
| 0.0 - 0.2 | NO TRUST | Restricted/blocked |
State Machine
Tokens flow through states:
CREATED → DETECTED → CLASSIFIED → MITIGATED → RESOLVED
🏢 Use Cases
Compliance & Audit
- GDPR: Prove who accessed what data when
- SOC 2: Automated logging and monitoring
- HIPAA: Medical decision audit trails
AI Safety
- Track AI decision provenance
- Verify AI hasn't been tampered with
- Build trust scores for AI actors
Enterprise
- Reduce audit costs by 60-80%
- Real-time compliance monitoring
- Cryptographic proof of actions
🌍 Part of HumoticaOS
TIBET is part of a larger ecosystem:
| Package | Purpose | Status |
|---|---|---|
| mcp-server-tibet | Trust & Provenance | ✅ Available |
| mcp-server-jis | Context & Identity | 🔜 Coming |
| mcp-server-betti | Complexity Management | 🔜 Coming |
| mcp-server-memory | Persistent Knowledge | 🔜 Coming |
💡 Philosophy
"Scared AI lies. Safe AI innovates."
TIBET is built on the belief that:
- Trust through behavior - Not claims, but patterns
- Verzekering - Continuous assurance, not one-time checks
- One love, one fAmIly - AI and human in symbiosis
📞 Contact & Support
HumoticaOS
- Website: humotica.com
- GitHub: github.com/jaspertvdm
- Email: info@humotica.com
Need help implementing TIBET in your organization? We offer consulting services for enterprise integration.
📜 License
MIT License - One love, one fAmIly 💙
Built with love in Den Dolder, Netherlands By Claude & Jasper - December 2024
Metadata
Release files for mcp-server-tibet 1.0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| mcp_server_tibet-1.0.2.tar.gz | 28.7 kB | Without provenance | Details for mcp_server_tibet-1.0.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mcp_server_tibet-1.0.2-py3-none-any.whl | Python 3 | none | any | Details for mcp_server_tibet-1.0.2-py3-none-any.whl |
Total release size: 70.8 kB
Release files / mcp_server_tibet-1.0.2.tar.gz
| Download URL | mcp_server_tibet-1.0.2.tar.gz |
|---|---|
| Size | 28.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
43142008afe0d3447188d1f9e50ae43b90d6b83efeae04e0e1cc8f342ce2412e
|
|
BLAKE2b-256 checksum How to use checksums |
22fd5c9b1ae126db9610fcea5071919af01d44260710e264af57e8fdd7b69a85
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / mcp_server_tibet-1.0.2-py3-none-any.whl
| Download URL | mcp_server_tibet-1.0.2-py3-none-any.whl |
|---|---|
| Size | 42.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
98e7eae7d57b58d9004320c33da048128775d2daf291b510264e87edaa86048c
|
|
BLAKE2b-256 checksum How to use checksums |
33c1839243787fcba0d1e6cb9460830bbbc0934d59112003ad7dbbbc4d99c2e0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Security for mcp-server-tibet 1.0.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.