checkMonitorsLABSCO SUMMARY
Ask what broke, then ship the monitor that catches it next time.
Most observability connections stop at read access. This one closes the loop: the agent investigates in APL, then creates the dashboard chart and the monitor in the same conversation. Query cost limits are the guardrail that makes letting it run unattended reasonable.
What it is
Axiom hosts this server at https://mcp.axiom.co/mcp. An agent gets your datasets, the APL query engine, and the dashboard, monitor and notifier objects around them.
What you get
- queryApl and queryMetrics run queries against your datasets; listDatasets and getDatasetSchema tell the agent what is there
- Dashboards created, updated, exported and deleted — updateDashboardChart patches a single chart by its ID instead of rewriting the whole document
- Monitors and notifiers created, updated and deleted, with checkMonitors for current status and getMonitorHistory for past alerts
- Metric discovery through listMetrics, listMetricTags, getMetricTagValues and searchMetrics
- Prebuilt prompts for anomaly detection, data quality investigation, performance baselines, cross-dataset correlation, monitor health and exploring a dataset nobody knows
Requirements
An Axiom account. The hosted endpoint uses OAuth and agents never see your token; an agent that cannot do browser OAuth sends a personal access token plus the organization ID as headers. Hosted query results route through US infrastructure.
Setup effort
Add the hosted endpoint, then sign in — paste it into your client, then approve the OAuth sign-in
USE CASES
01
Finding out what broke in the last half hour
Fetch the dataset schema, then run the APL that groups status codes over the window — each is a single tool call.
02
Standing up a dashboard for a service that never had one
Explore the dataset, create the dashboard from a JSON document, then patch individual charts by ID as you refine it.
03
Turning a one-off investigation into an alert
Create the monitor and the notifier while the pattern is still on screen, and read its alert history later.
04
Capping what an autonomous agent can spend
Set query cost limits on the API token for a local run, or on your roles for the hosted server, where OAuth makes the agent act as your account.
25 tools
Listed in project docs. Your client may show a different list.
createDashboardcreateMonitorcreateNotifierdeleteDashboarddeleteMonitordeleteNotifierexportDashboardgetDashboardgetDatasetSchemagetMetricTagValuesgetMonitorHistorygetSavedQuerieslistDashboardslistDatasetslistMetricTagslistMetricslistNotifiersqueryAplqueryMetricssearchMetricsupdateDashboardupdateDashboardChartupdateMonitorupdateNotifierBEFORE YOU INSTALL
What to know first
Tools you get
25 tools named in the project's documentation.
Requires
An Axiom account
Where it runs
The documented client connects to a hosted endpoint.
INSTALLATION
Connect your client
Server setup
ENDPOINT URL
https://mcp.axiom.co/mcpAdd this hosted endpoint to your MCP client, then sign in.
MCP Clients
Claude Desktop — remote
CLAUDE DESKTOP — REMOTE · JSON
{
"mcpServers": {
"axiom": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.axiom.co/mcp"
]
}
}
}
