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