Kanonik

Governance runtime for compliance: verified, human-approved writes to a tamper-evident record.

LLM Mart 13 views 110 listing impressions
Transport
Not stated
Package
Registry id
ai.kanonik/kanonik

No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.

Kanonik is a governance runtime that checks every draft against your framework, gets approved by a named person, and is sealed into a tamper-evident record that auditors can verify on their own. It works with existing AI tools by using skills to shape outputs and a server-side Verifier that runs before anything is committed, ensuring nothing unproven enters the record. Every consequential write requires a named person's approval in the browser, scoped to that one change, ensuring human oversight.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Related servers

Free deterministic security scan of public git repos: OSV.dev vulnerable deps, secrets, config lint.

6 views

Production-safety audits for AI-generated code, with a fix for every finding.

5 views

Runtime verification for agent tool calls: Ed25519 signed receipts, fail-closed RCE/SSRF checks.

2 views

Solana token/wallet rug-risk scoring. Free scan; $2 SOL unlocks full wallet report. No signup.

0 views