Metricwatch runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 1 Nov 2026.
Datadog metrics, dashboards, logs, incidents, and monitors from your MCP client.
Today is the operative word: we check Metricwatch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 metricwatch -- npx -y @reneturcios/metricwatch
{
"mcpServers": {
"metricwatch": {
"command": "npx",
"args": [
"-y",
"@reneturcios/metricwatch"
]
}
}
}
[mcp_servers.metricwatch]
command = "npx"
args = ["-y", "@reneturcios/metricwatch"]
{
"mcpServers": {
"metricwatch": {
"command": "npx",
"args": [
"-y",
"@reneturcios/metricwatch"
]
}
}
}
{
"servers": {
"metricwatch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/metricwatch"
]
}
}
}
Datadog MCP — 165 tools for metrics, monitors, logs, APM, RUM, incidents, CI/CD, fleet
Grafana dashboards, datasources, Prometheus, Loki, and alerts from your MCP client.
Full Datadog API access: monitors, logs, metrics, traces, dashboards, and observability tools
Manage uptime monitors, incidents and status pages from any MCP client.
Manage CronAlert uptime monitors, check results, and incidents from any MCP client.
Manage uptime monitors and incidents and search logs, metrics and traces from an AI assistant.
Independent monitoring: status, monitors, and incidents from your StackWitness workspace.
Ask your AI what's broken: incidents, monitors, servers, logs, errors and traces from Vigil.
Answers built from our own checks of this server.