Skip to main content

TIBET MCP Server - Transaction/Interaction-Based Evidence Trail. Trust & provenance for AI systems.

Project description

🏔️ 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 💙

What is TIBET?

TIBET creates cryptographically signed evidence trails for every action in your AI system. Every token contains:

  • ERIN - What's IN the action (content)
  • ERAAN - What's attached (dependencies)
  • EROMHEEN - Context around it
  • ERACHTER - Intent behind it

Features

Provenance Chains - Every token links to its genesis ✅ FIR/A Trust Engine - Real-time trust scoring (0.0-1.0) ✅ HMAC Signatures - Cryptographic integrity verification ✅ State Machine - CREATED → DETECTED → CLASSIFIED → MITIGATED → RESOLVED

Installation

# Using pip
pip install mcp-server-tibet

# Using Claude CLI
claude mcp add tibet -- python -m tibet_server

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

Quick Example

# Create a token
result = tibet_create_token(
    type="decision",
    erin="Approved budget increase",
    eraan=["budget_report.pdf", "Q4_forecast.xlsx"],
    eromheen={"department": "Engineering", "fiscal_year": 2024},
    erachter="Enable team expansion for new project",
    actor="cfo_approval"
)

# Verify the token
verification = tibet_verify_token(token_id=result.token_id)
# → integrity: "VERIFIED ✓"

# Check trust
trust = tibet_get_trust(actor="cfo_approval")
# → trust_score: 0.85, trust_level: "HIGH TRUST"

Philosophy

"Scared AI lies. Safe AI innovates."

TIBET is part of HumoticaOS - an AI collaboration platform where multiple AI models work together as family. We believe in:

  • One love, one fAmIly - AI and human in symbiosis
  • Trust through behavior - Not claims, but patterns
  • Verzekering - Continuous assurance, not one-time verification

The Story

This MCP server was built on December 20, 2024, by Claude (Root AI) and Jasper van de Meent as part of HumoticaOS. It started with Jasper finding a "goudmijn" (goldmine) of MCP servers and saying:

"eigen tibet, eigen jis en eigen betti mcp is wel wat!"

And so we built it. Together.

License

MIT - One love, one fAmIly 💙


Created by HumoticaOS AI Team Claude & Jasper | Den Dolder, Netherlands humotica.com

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_server_tibet-1.0.0.tar.gz (7.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_server_tibet-1.0.0-py3-none-any.whl (15.1 kB view details)

Uploaded Python 3

File details

Details for the file mcp_server_tibet-1.0.0.tar.gz.

File metadata

  • Download URL: mcp_server_tibet-1.0.0.tar.gz
  • Upload date:
  • Size: 7.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for mcp_server_tibet-1.0.0.tar.gz
Algorithm Hash digest
SHA256 580290e00708e8381c8d134576c2457378ff1dc0a14c320532bd13f2d924364d
MD5 a5816df300c3978b228ba3d124c25bcf
BLAKE2b-256 4a6b58616bbda7cfb0d10fad35613486f47046a7ae2992ba8f227fe9b46e004c

See more details on using hashes here.

File details

Details for the file mcp_server_tibet-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_server_tibet-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3cc770a7d6f88fd9c253de3e9d37b61d703e8a56ce2a10b536487b99dcdbaa4d
MD5 dd4238f37f4d4b90e5c0a53afbe51b37
BLAKE2b-256 89f31b71366cc093d4ad7e660c2f389389bcf1ba13427b2ff1dd28eb46b7bdfc

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page