Korext: AI Code Governance is answering right now. Last checked 4 min ago. 89 installs a week from npm. It exposes 5 tools. Last commit 17 Apr 2026.
Governance copilot for AI-assisted coding. 72 packs, 532 rules, proof bundles.
We read the source, 21 h ago · tools taken from the live server · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
if (platform === 'darwin') execSync(`open ${url}`);
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
eval(req.body.code);
if (platform === 'darwin') execSync(`open ${url}`);
const files = fs.readdirSync(dir);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Korext: AI Code Governance and you get told the day something new turns up.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.
claude mcp add governance --transport http https://app.korext.com/api/mcp
{
"mcpServers": {
"governance": {
"url": "https://app.korext.com/api/mcp"
}
}
}
[mcp_servers.governance]
url = "https://app.korext.com/api/mcp"
{
"mcpServers": {
"governance": {
"url": "https://app.korext.com/api/mcp"
}
}
}
{
"mcpServers": {
"governance": {
"url": "https://app.korext.com/api/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
check_code
get_directives
generate_proof
list_packs
get_proof
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://app.korext.com/api/mcp | streamable-http | answering | 402 ms | 4 min ago |
New Relic MCP server for observing AI coding assistants (Claude Code, Cursor, Copilot, etc.)
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Social layer for Claude Code - DMs, presence, games between AI-assisted developers
Social layer for Claude Code - DMs, presence, discovery, and games between AI-assisted developers
Persistent, evidence-backed code graph for coding agents.
Persistent code indexing for AI assistants. 50x less context than grep. 11 languages.
Governance runtime for AI-generated code. Enforce compliance and security standards.
Turn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot.
Answers built from our own checks of this server.