EZO Watcher runs on your own machine — the client starts it, so there is no endpoint to ping. 378 installs a week from npm. Last commit 5 Nov 2026.
Self-hosted monitoring your coding agent installs, proves and fixes. Alert wall, pager, MCP.
We read the source, 1 d ago · rules 995398eba69f
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.
if (exists('/.dockerenv')) return 'docker'
const child = spawn(bin, ['tunnel', '--url', local], { stdio: ['ignore', 'pipe', 'pipe'] })
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 ezo-watcher -- npx -y ezo-watcher
{
"mcpServers": {
"ezo-watcher": {
"command": "npx",
"args": [
"-y",
"ezo-watcher"
]
}
}
}
[mcp_servers.ezo-watcher]
command = "npx"
args = ["-y", "ezo-watcher"]
{
"mcpServers": {
"ezo-watcher": {
"command": "npx",
"args": [
"-y",
"ezo-watcher"
]
}
}
}
{
"servers": {
"ezo-watcher": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ezo-watcher"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
WATCHER_MCP_TOKEN (Token for the running Watcher's /mcp endpoint. When unset it is read from the project's .watcher/.env).
An MCP server that provides tools for managing and monitoring your Fleet Device Management instance.
AI agent monitoring: alerts when your agents fail, stall or need you
Stacks contract monitoring: add a watch in one line, get alerts. Hosted, browser sign-in.
Agent-run site monitoring: install JAMP, read errors, uptime, vitals and traffic, resolve fixes.
MCP server for Hatchbox Rails hosting — env var inspection, deploys, and process monitoring.
Your coding agent adds Probecast uptime monitors and reads incidents for projects you ship.
Health monitoring for all your MCP servers
Uptime monitoring and status pages for apps built with coding agents: status, incidents, setup.
Answers built from our own checks of this server.