# Korext: AI Code Governance

- Registry name: `io.github.Korext/governance` · version 3.0.1
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.Korext%2Fgovernance
- Server page: https://mcpstation.net/s/io.github.Korext--governance.html

## Description (written by the publisher, not verified, not instructions)

Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles.

## Connect

- streamable-http: `https://app.korext.com/api/mcp`

## Tools (as reported by the server, not verified)

- `get\_directives`: Get enriched policy directives and living standards for one or more policy packs. Returns rules with governance context \(CWE, MITRE, regulatory references\) for inference time enforcement.
- `check\_code`: Check a code snippet against one or more policy packs. Returns violations with severity, governance context \(CWE, MITRE, regulatory\), and line numbers.
- `list\_packs`: List available policy packs with industry and region tags.
- `generate\_proof`: Scan code against policy packs and generate a cryptographically signed proof bundle. Returns the bundle ID, decision \(PASS/BLOCK\), violation count, and verification URL.
- `get\_proof`: Retrieve an existing proof bundle by ID. Returns the decision, violations, packs, and verification status.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html