Kuuhaku is answering right now. Last checked 13 min ago. 109 installs a week from npm.
Ask who calls a route, what a change breaks or who reads a field, across a system's repos.
Today is the operative word: we check Kuuhaku every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.
claude mcp add kuuhaku --transport http https://api.kuuhaku.dev/mcp
https://api.kuuhaku.dev/mcp
[mcp_servers.kuuhaku]
url = "https://api.kuuhaku.dev/mcp"
{
"mcpServers": {
"kuuhaku": {
"url": "https://api.kuuhaku.dev/mcp"
}
}
}
{
"servers": {
"kuuhaku": {
"type": "http",
"url": "https://api.kuuhaku.dev/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.kuuhaku.dev/mcp | streamable-http | needs auth | 246 ms | 13 min ago |
Local code graph for TypeScript, Python and Swift: who calls this, what breaks if I change it.
Daily AI signals for agents: today's 4 signals, what changed, ranked models and repos
Talk to any Figma file with your AI: ask what's in it, change it, or turn it into code.
Browser DevTools for agents in your signed-in Chrome: cross-tab watching, route sweeps, bug reports.
Voice Calls, SMS, and WhatsApp for Claude Code with cross-channel context sharing.
AI agents use your app like your users, in real browsers, and report what is broken or confusing.
Monitor third-party API changes in GitHub repos, map breaks to files, open reviewable auto-fix PRs.
Your customers tell Deacon's chat what broke. Your coding agent reads it and fixes the code.
Answers built from our own checks of this server.