Phoenix Zero — L2 Health Oracle runs on your own machine — the client starts it, so there is no endpoint to ping. 176 installs a week from npm. Last commit 17 Sep 2026.
Pre-flight L2 health check using kernel-level eBPF telemetry. PASS/DEGRADED/FAIL verdict.
We read the source, 17 h ago · rules 3dff92dd89df
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.
out = subprocess.check_output(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add phoenix-mcp-server -- npx -y phoenix-mcp-server
{
"mcpServers": {
"phoenix-mcp-server": {
"args": [
"-y",
"phoenix-mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.phoenix-mcp-server]
command = "npx"
args = ["-y", "phoenix-mcp-server"]
{
"mcpServers": {
"phoenix-mcp-server": {
"args": [
"-y",
"phoenix-mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"phoenix-mcp-server": {
"args": [
"-y",
"phoenix-mcp-server"
],
"command": "npx"
}
}
}
Pre-transaction health and safety verdicts for onchain apps, by contract address.
Deterministic pre-execution audit for trading agents. PASS/WAIT/FAIL, reproducible verdict_hash.
Loudness compliance verdicts (EBU R128, ATSC A/85): pass/fail with exact ffmpeg remediation.
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
Dependency intelligence for AI agents. CVE scanning, health checks, upgrade planning.
Dependency intelligence for AI agents. CVE scanning, health checks, upgrade planning.
Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.
Trust registry for agents: check_trust verdict A0-A4, signed fact passports, honest refusals.
Answers built from our own checks of this server.