firetiger

You have access to Firetiger, an AI-powered observability platform, through MCP tools.

Use when creating a Firetiger monitoring agent, installing a prebuilt catalog agent, or configuring an agent's triggers and schedules — monitoring something automatically, scheduling recurring or one-off analysis, or wiring event-driven automation. Always use this skill to create or automate an agent — it carries the critical gotchas (prefer create_agent_with_goal and answer the planner, agents must be AGENT_STATE_ON to fire, triggers are separate resources with six config types, scheduled-agent-runs are one-shot not cron).

Use when adding OpenTelemetry instrumentation to an application so it sends telemetry to Firetiger — setting up tracing, configuring the OTLP exporter, or connecting a Node.js, Next.js, Python, Go, or Rust app to Firetiger. Always use this skill when instrumenting for Firetiger — it carries the critical gotchas (init must load before any other import, Firetiger ingest uses HTTP Basic auth not Bearer, credentials come from the get_ingest_credentials MCP tool) that make telemetry actually show up.

Use when diagnosing an issue or incident with Firetiger — launching or reading a Firetiger investigation, troubleshooting with telemetry, or working the issues an investigation surfaces. Always use this skill for incident diagnosis — it carries the critical gotchas (an investigation is an AI agent session, not a findings form; its status is server-set; issues are managed by an expert agent you steer rather than mutate) that keep you working with the product instead of against it.

Use when monitoring a PR or deployment with Firetiger and reviewing what it found — watching a deploy, setting up the @firetiger comment flow, registering deployments from CI/CD, or reading a monitoring agent's results. Always use this skill for deploy monitoring — it carries the critical gotchas (monitor_pr needs the full PR URL, the @firetiger flow needs a connected GitHub App, checks run at 10m/1h/24h/72h anchored to the real deploy, register deploys with Basic auth so checkpoints fire on the right release).

Use when querying Firetiger telemetry with SQL — finding traces, searching logs, inspecting metrics, locating errors or slow requests, computing latency percentiles, aggregating observability data, or querying a connected source (Postgres, MySQL, ClickHouse, Datadog, Prometheus, GCP Monitoring) through the Firetiger MCP `query` tool. Always use this skill before writing a Firetiger query — it carries the critical gotchas (slashed table names must be quoted, duration is computed not stored, status codes are integers, attributes are structs not maps, fully-qualify "connections/{name}".table to reach a connected source) that make queries succeed.