Skip to main content

MCP Server for TIBET - The Trust Kernel for AI. Audit as a Precondition, Not an Afterthought.

Project description

mcp-server-tibet-core

The Trust Kernel for AI - MCP Server

Audit as a Precondition, Not an Afterthought.

MCP (Model Context Protocol) server that gives Claude, Codex, Gemini, and other AI assistants full TIBET provenance capabilities.

Installation

pip install mcp-server-tibet-core

Quick Start

Add to your Claude Desktop config (~/.config/claude/claude_desktop_config.json):

{
  "mcpServers": {
    "tibet-core": {
      "command": "mcp-server-tibet-core"
    }
  }
}

Restart Claude Desktop. Now your AI can create provenance tokens for every action!

Available Tools

Tool Description
tibet_create Create a provenance token BEFORE any action
tibet_verify Verify a token's integrity
tibet_chain Get full provenance chain for a token
tibet_export Export audit trail (JSON/markdown/summary)
tibet_list List recent tokens
tibet_status Get TIBET provider status

TIBET Provenance Model

Every action is documented with four dimensions:

  • ERIN (what's IN) - The content/data of the action
  • ERAAN (attached) - Dependencies and references
  • EROMHEEN (around) - Context and environment
  • ERACHTER (behind) - The WHY - intent and purpose

Example Usage

When your AI performs an action, it can now document it:

AI: I'll create a TIBET token before modifying this file.

[tibet_create]
- action: "file_write"
- erin: {"file": "config.py", "changes": "Added API key validation"}
- erachter: "Improve security by validating API keys before use"
- eraan: ["issue-123", "security-audit-2024"]
- eromheen: {"branch": "main", "user": "jasper"}

Token created: tbt_abc123...

Now you have an immutable audit record of what the AI did and why.

Why TIBET?

  • Compliance Ready: AI Act, NIS2, GDPR, DORA
  • Audit Trail: Every action documented before execution
  • Trust Kernel: Like TPM for hardware, but for AI actions
  • Enterprise Grade: Used by 1,162+ enterprise mirrors

Links

Philosophy

"Don't ask what your AI did. Know before it acts."

Every AI action, documented before execution. Compliance built-in, not bolted-on. One kernel. Every AI. Full provenance.


One love, one fAmIly!

MIT License - Humotica 2024-2026

License

MIT

Credits

Designed by Jasper van de Meent. Built by Jasper and Root AI as part of HumoticaOS.


Stack-positie: Groep agentic · Bootstrap = OSAPI-handshake naar tibet + jis (fail → snaft-rule + tibet-pol-rapport) · ← tibet-core · mcp-server-tibet → · See STACK.md · See demo/golden-path/ for the spine end-to-end.

Enterprise

For private hub hosting, SLA support, custom integrations, or compliance guidance:

Enterprise enterprise@humotica.com
Support support@humotica.com
Security security@humotica.com

See ENTERPRISE.md for details.

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_core-0.1.1.tar.gz (7.4 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_core-0.1.1-py3-none-any.whl (7.0 kB view details)

Uploaded Python 3

File details

Details for the file mcp_server_tibet_core-0.1.1.tar.gz.

File metadata

  • Download URL: mcp_server_tibet_core-0.1.1.tar.gz
  • Upload date:
  • Size: 7.4 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_core-0.1.1.tar.gz
Algorithm Hash digest
SHA256 c47548c237c59c9c11e46c368c0af58a2b9d03b09f1309addc26d77c0227f4a1
MD5 f2fca62456b4368d7c39a6853210fec0
BLAKE2b-256 8c7ebc62631f065a2a4b1765a62cdc14b8762eddc29557cafb93e660140c3202

See more details on using hashes here.

File details

Details for the file mcp_server_tibet_core-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_server_tibet_core-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 7dc9667a1b73474ed109a1821dd5fff77645fa24015c091f128c42bf576d75cd
MD5 0c46a51399c0d67db4d81b84a867e3f2
BLAKE2b-256 bac2fda02d60e0b69dd5f69a9088370c8c37f342dc454feb023342dbdafee4af

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