# Faultline

Connects AI assistants to Faultline infrastructure monitoring to inspect incidents, check service health, and run runbooks.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: fltln-io
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/fltln-io/faultline-mcp
- Updated: 2026-07-04
- HTML: https://affpapa.org/en/nevibecode/mcp/faultline

## What it does

Faultline runs this remote MCP server at `https://mcp.fltln.io/mcp` using Streamable HTTP. You do not run any local binaries. Access requires an API key starting with `flt_...` generated inside your Faultline settings.

The toolset lets your agent pull service inventories, read the 10 most recent health checks, track latency baseline anomalies, and look up on-call shifts. To investigate outages, `diagnose_incident` provides next-step suggestions without modifying resources.

The only tool that touches your infrastructure is `run_runbook`. It can scale or reboot services, meaning agents should trigger it only after explicit confirmation. Every API call remains strictly isolated within your organization account.

## Requirements
- Remote server: `https://mcp.fltln.io/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http faultline https://mcp.fltln.io/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add faultline --url https://mcp.fltln.io/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "faultline": {
            "url": "https://mcp.fltln.io/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "faultline": {
            "type": "http",
            "url": "https://mcp.fltln.io/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http faultline https://mcp.fltln.io/mcp
```

## When to use it
- inspect service health along with its 10 latest checks
- retrieve on-call engineer schedules and shift handoff times
- review latency anomalies against calculated baseline values
- execute verified runbooks to restart or scale struggling services

## Example prompts
- Who is currently on call and when does their shift end?
- Check the last 10 health checks for the auth-service.
- Run diagnose_incident on the active incident and suggest runbooks.

## Similar
- [devops-automation](https://affpapa.org/en/nevibecode/skills/devops-automation.md) — skill · 4800 installs
- [devops-incident-responder](https://affpapa.org/en/nevibecode/agents/devops-incident-responder.md) — subagent · 206 installs
- [incident-responder](https://affpapa.org/en/nevibecode/agents/incident-responder.md) — subagent · 265 installs
- [azure-sre-agent](https://affpapa.org/en/nevibecode/plugins/azure-sre-agent.md) — plugin · ★ 2
- [sre-engineer](https://affpapa.org/en/nevibecode/skills/sre-engineer.md) — skill · 5100 installs
- [incident-response](https://affpapa.org/en/nevibecode/plugins/incident-response.md) — plugin · ★ 41887

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md