Korext: AI Code Governance is an MCP server published by io.github.Korext, hosted at app.korext.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 5 tools, including get_directives, check_code, list_packs, generate_proof, get_proof.
Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles.
199 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| packId | any | Policy pack ID or array of IDs (e.g. 'web', ['web', 'pci-dss-v1']). Defaults to 'web'. |
{
"name": "get_directives",
"description": "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.",
"inputSchema": {
"type": "object",
"properties": {
"packId": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
],
"description": "Policy pack ID or array of IDs (e.g. 'web', ['web', 'pci-dss-v1']). Defaults to 'web'."
}
}
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Check a code snippet against one or more policy packs. Returns violations with severity, governance context (CWE, MITRE, regulatory), and line numbers.
| Parameter | Type | Description |
|---|---|---|
| code * | string | The code snippet to check. |
| packId | any | Policy pack ID or array of IDs. Defaults to 'web'. |
{
"name": "check_code",
"description": "Check a code snippet against one or more policy packs. Returns violations with severity, governance context (CWE, MITRE, regulatory), and line numbers.",
"inputSchema": {
"type": "object",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"description": "The code snippet to check."
},
"packId": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
],
"description": "Policy pack ID or array of IDs. Defaults to 'web'."
}
}
}
}List available policy packs with industry and region tags.
| Parameter | Type | Description |
|---|---|---|
| region | string | Filter by region (e.g. us, eu, uk, global) |
| industry | string | Filter by industry (e.g. finance, healthcare, defense, aerospace, energy, technology) |
{
"name": "list_packs",
"description": "List available policy packs with industry and region tags.",
"inputSchema": {
"type": "object",
"properties": {
"region": {
"type": "string",
"description": "Filter by region (e.g. us, eu, uk, global)"
},
"industry": {
"type": "string",
"description": "Filter by industry (e.g. finance, healthcare, defense, aerospace, energy, technology)"
}
}
}
}Scan code against policy packs and generate a cryptographically signed proof bundle. Returns the bundle ID, decision (PASS/BLOCK), violation count, and verification URL.
| Parameter | Type | Description |
|---|---|---|
| code * | string | The code to scan. |
| packId | any | Policy pack ID(s). Defaults to 'web'. |
| fileName | string | File name for context |
| language | string | Programming language (typescript, python, etc.) |
{
"name": "generate_proof",
"description": "Scan code against policy packs and generate a cryptographically signed proof bundle. Returns the bundle ID, decision (PASS/BLOCK), violation count, and verification URL.",
"inputSchema": {
"type": "object",
"required": [
"code"
],
"properties": {
"code": {
"type": "string",
"description": "The code to scan."
},
"packId": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
],
"description": "Policy pack ID(s). Defaults to 'web'."
},
"fileName": {
"type": "string",
"description": "File name for context"
},
"language": {
"type": "string",
"description": "Programming language (typescript, python, etc.)"
}
}
}
}Retrieve an existing proof bundle by ID. Returns the decision, violations, packs, and verification status.
| Parameter | Type | Description |
|---|---|---|
| bundleId * | string | The proof bundle ID (kpb_...) |
{
"name": "get_proof",
"description": "Retrieve an existing proof bundle by ID. Returns the decision, violations, packs, and verification status.",
"inputSchema": {
"type": "object",
"required": [
"bundleId"
],
"properties": {
"bundleId": {
"type": "string",
"description": "The proof bundle ID (kpb_...)"
}
}
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.