Faultline

Connect Remote server

claude mcp add --transport http faultline https://mcp.fltln.io/mcp --header "X-API-Key: <X_API_KEY>"

{
  "mcpServers": {
    "faultline": {
      "url": "https://mcp.fltln.io/mcp",
      "headers": {
        "X-API-Key": "<X_API_KEY>"
      }
    }
  }
}

{
  "servers": {
    "faultline": {
      "type": "http",
      "url": "https://mcp.fltln.io/mcp",
      "headers": {
        "X-API-Key": "<X_API_KEY>"
      }
    }
  }
}

Settings > Connectors > Add custom connector
URL: https://mcp.fltln.io/mcp

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools 10 found in our last check

• list_services

  List all monitored services with their current status (OK, DEGRADED, DOWN, PAUSED, PENDING). Call this first to get an overview of infrastructure health, or to find a service's ID.

• get_service

  Get one service's details including its 10 most recent health checks (status codes, latency, errors). Call this when diagnosing WHY a service is degraded or down.

• list_incidents

  List incidents — open ones by default, or recently resolved with status='resolved'. Call this when asked about outages, what's broken, or incident history.

• get_incident

  Get an incident's full record: timeline of every update, escalations, runbook results, AI summary, and post-mortem if drafted. Call this before acting on an incident.

• acknowledge_incident

  Acknowledge an open incident, stopping further escalation. Call this when the user says they are looking into an incident or asks you to take ownership of it.

• resolve_incident

  Mark an incident as resolved, with an optional note describing the fix. Only call this when the user confirms the underlying issue is fixed — resolving is a status-page-visible action.

• who_is_on_call

  Get the person currently on call for each on-call schedule, and when their shift ends. Call this when deciding who to contact about an incident.

• list_anomalies

  List recent learned-baseline latency anomalies: observed vs baseline response time, the deviation z-score, how many consecutive hours it has been sustained, and the incident it auto-opened (if any). Call this when asked why a service is slow, about latency spikes, or for early d…

• diagnose_incident

  Analyze an open incident and recommend the next action: run a specific runbook, escalate to a human, resolve, or wait. Returns the recommendation (with rationale and confidence) and the candidate runbooks. This is analysis ONLY — it does not change anything. Call this to decide…

• run_runbook

  Execute one specific runbook against an incident. This MUTATES INFRASTRUCTURE (it can restart or scale services). Only call after diagnose_incident recommended it AND the user has confirmed. Pass the runbookId from the diagnosis's recommendation or candidate list.

Headers

Details

More other servers See all

• SalaryNet Payroll

  Gross-to-net pay and employer cost for US, PH, NG, ID, IN, BR, KE, VN with official sources.

• Auto Öz

  Auto Öz: Kontakt, Standorte, Öffnungszeiten, Leistungen und Angebote, Freie Termine, Termin…

• CGC Airport Transfers

  Fixed-price quotes and bookings for private airport transfers: Gold Coast, Brisbane, Byron Bay.

• Coral

  Private, non-explicit intimacy exercises, scripts and a couples quiz for adults 18+.

• Business valuation calculator

  Estimates what a buyer might pay for a small agency, service or SaaS business, in US dollars.

• BuildYourWolfpack

  Roast-to-order coffee with a game built in: missions, Pack Points, and your own wolf pack.