Agents Index

Faultline

Online

Check infrastructure health, manage incidents, and run runbooks in Faultline.

Visit publisherConnectJSON

What it can do: 10 tools

  • list_services read-onlyList 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 read-onlyGet 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 read-onlyList 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 read-onlyGet 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_incidentAcknowledge 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_incidentMark 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 read-onlyGet 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 read-onlyList 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
  • diagnose_incident read-onlyAnalyze 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 analys
  • run_runbookExecute 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 d

Connect it

Claude Code
claude mcp add --transport http faultline https://mcp.fltln.io/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.fltln.io/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "faultline": {
      "url": "https://mcp.fltln.io/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "faultline": {
      "type": "http",
      "url": "https://mcp.fltln.io/mcp"
    }
  }
}

Questions

What does Faultline do?

Check infrastructure health, manage incidents, and run runbooks in Faultline. It exposes 10 tools to AI assistants.

What tools does Faultline provide?

10 tools, including list_services, get_service, list_incidents, get_incident, acknowledge_incident, resolve_incident, who_is_on_call, list_anomalies, diagnose_incident, run_runbook.

How do I connect Faultline to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.fltln.io/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Faultline require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Faultline online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Faultline?

fltln.io. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Cloud & DevOps