{
  "markdown": "# Faultline MCP Server\n\n[Faultline](https://fltln.io) is infrastructure monitoring and incident\nmanagement for DevOps/SRE teams. This repo documents `faultline-mcp` —\nFaultline's remote MCP server, which lets AI agents (Claude, Claude Code,\nClaude Desktop, or anything MCP-compatible) operate Faultline: check\ninfrastructure health, inspect and act on incidents, look up who's on call,\nand run approved runbooks.\n\n**This repo is documentation only.** The server is hosted by Faultline at\n`https://mcp.fltln.io/mcp` (Streamable HTTP transport) — there's nothing to\ninstall or run yourself.\n\n## Setup\n\n1. Create an API key in Faultline: **Settings → API Keys**. Keys look like\n   `flt_...`.\n2. Point your MCP client at `https://mcp.fltln.io/mcp`, sending the key as\n   either `X-API-Key: flt_...` or `Authorization: Bearer flt_...`.\n\n**Claude Code:**\n\n```bash\nclaude mcp add --transport http faultline-mcp https://mcp.fltln.io/mcp \\\n  --header \"X-API-Key: flt_...\"\n```\n\n**Clients that take raw JSON config** (Claude Desktop, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"faultline\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.fltln.io/mcp\",\n      \"headers\": { \"X-API-Key\": \"flt_...\" }\n    }\n  }\n}\n```\n\n## Tools\n\n| Tool | What it does |\n| --- | --- |\n| `list_services` | Monitor inventory with current status (optional status filter) |\n| `get_service` | One service + its 10 most recent checks (for diagnosis) |\n| `list_incidents` | Open incidents (or `status: \"resolved\"` for history) |\n| `get_incident` | Full incident record: timeline, AI summary, post-mortem |\n| `acknowledge_incident` | Acknowledge an incident — stops further escalation |\n| `resolve_incident` | Resolve with an optional note (recorded on the timeline) |\n| `who_is_on_call` | Current on-call per schedule, with shift end time |\n| `list_anomalies` | Recent learned-baseline latency anomalies (observed vs baseline, z-score, hours sustained, auto-opened incident if any) |\n| `diagnose_incident` | Recommend the next action (run runbook / escalate / resolve / wait) + candidate runbooks. Analysis only — changes nothing |\n| `run_runbook` | Execute one chosen runbook against an incident — **mutates infrastructure** (can restart/scale services) |\n\n## Security\n\n- **Scoped to your API key.** The server never stores your key — it's used\n  only for the duration of each request, proxied straight through to\n  Faultline's API.\n- **Approval-gated mutation.** `run_runbook` is the only tool that changes\n  infrastructure. Its description instructs the calling agent to use it only\n  after `diagnose_incident` recommended it and you've explicitly confirmed.\n- **Tenant-isolated.** Every request is scoped to the tenant that owns the\n  API key — one key can never see or affect another tenant's data.\n\n## Support\n\nQuestions or issues: [support@fltln.io](mailto:support@fltln.io) or the\n[Faultline dashboard](https://fltln.io).\n",
  "bytes": 2888,
  "sha": "ca56eeb3b0f000592653f961b7fc66417ce6e6570986afbc3287677df3c0272d",
  "repo_slug": "fltln-io/faultline-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_fltln_faultline_c9f64fc4/readme"
}