Bronto

Bronto is an observability data platform built for petabyte scale: sub-second search across 12 months of always-hot retention, no rehydration, no waiting on archives.

This connector gives Claude direct access to your live telemetry. Ask what's happening in production and Claude works the way an engineer would: find the relevant datasets, inspect their schemas and field values, build precise filters, then search raw events or aggregate them into trends and percentiles. You describe what you're looking for instead of needing the query language up front.

Investigations don't have to end when you find the answer. Claude can turn the query that exposed a problem into a monitor so it's caught automatically next time, save the useful views for your team as timeseries, top-lists, tables or geomaps, and attach an investigation playbook that runs when the monitor fires — so on-call starts from a diagnosis rather than a blank page. Monitors are always created muted, so nothing pages anyone until you've reviewed it in Bronto.

You can also ask about coverage itself: which datasets are ingesting but unmonitored, which are heavily ingested but never searched, which have gone stale, and where errors are concentrated.

What Claude can do:

Discover datasets, inspect schemas, and search raw telemetry events over any time range

Aggregate with counts, sums, averages, percentiles, grouping, and time bucketing

Create, find, and re-run saved searches with tags and custom visualizations

Create threshold and no-data monitors, muted for review, with optional AI investigation prompts

Health-check existing monitors to spot ones that have silently stopped working

Audit per-dataset monitoring, search, and ingestion coverage, and pull org-wide error summaries at no search cost

Authentication uses your existing Bronto login — OAuth, SSO, or Google Social — and admins control which login methods are permitted for MCP access. Connect the endpoint for your data region, EU or US.