Incident Management MCP Server
Alerts, diagnostics, playbooks — from Claude Code, Cursor, or Codex
Connect mttrly to your AI coding assistant via the Model Context Protocol. The first dedicated incident management MCP server: view alerts, run AI diagnostics, execute remediation playbooks — without leaving your IDE.
https://api.mttrly.com/mcpQuick Start
Add mttrly to your MCP client. One config — instant access to your servers.
Claude Code
bashclaude mcp add mttrly --transport http https://api.mttrly.com/mcp
Run this in your terminal. OAuth login opens in browser automatically.
Cursor
json{
"mcpServers": {
"mttrly": {
"url": "https://api.mttrly.com/mcp"
}
}
}Go to Cursor → Settings → Cursor Settings → MCP → Add server.
Claude Desktop
json{
"mcpServers": {
"mttrly": {
"url": "https://api.mttrly.com/mcp"
}
}
}Open Settings → Developer → Edit Config. Add to claude_desktop_config.json.
OpenAI Codex
toml[mcp_servers.mttrly] url = "https://api.mttrly.com/mcp"
Add to ~/.codex/config.toml. Run codex mcp login mttrly for OAuth.
What you can ask
Talk to your servers in plain English. Here are some examples.
Returns active alerts with severity, timestamps, and affected servers. Watchdog plan and above.
AI-powered diagnostic checks CPU, RAM, disk, processes, and logs. Returns summary with raw output. 30s cooldown.
Lists remediation playbooks filtered by category, with required parameters and approval requirements.
Creates a pending action. You confirm before anything runs. Approval and execution are recorded in the audit trail.
Available tools
mttrly exposes 11 MCP tools organized into read and execute groups.
Read (all plans)
mttrly_get_capabilitiesGet current plan, available tools, and limits. Call this first.mttrly_list_serversList all connected servers with online/offline status and server IDs.mttrly_get_server_statusDetailed server health: CPU, RAM, disk, active alerts, OS info.mttrly_get_alertsGet alerts with severity/status filtering. Plan-based retention limits.mttrly_run_diagnosticAI-powered server diagnostic. Describe the problem — get targeted checks and raw output. 30s cooldown.mttrly_list_playbooksList remediation playbooks with categories and approval requirements.Execute (Deployment Bro+)
mttrly_run_playbookExecute a remediation playbook. Dangerous ones require explicit approval.mttrly_execute_commandRun a shell command. Always requires approval. Approval and execution are recorded in the audit trail.mttrly_get_pending_actionsList actions awaiting your approval with expiration times.mttrly_approve_actionApprove or reject a pending action. Blocks until execution completes.mttrly_get_audit_logAudit trail: approval decisions, command executions, playbook runs, agent fixes.Security & Safety
OAuth 2.1
Full spec: PKCE S256, JWT RS256, refresh token rotation with reuse detection. OAuth browser login is recommended, and API keys are also supported from your dashboard.
Approval gates
Destructive actions always require explicit confirmation. Your AI assistant asks — you decide.
Audit log
Approval decisions, command executions, playbook runs, and remediation actions are recorded with timestamps for review.
Plan-based access
Read tools available on all plans. Execution tools require Deployment Bro. No silent 403s — the capabilities tool tells the agent what's available.
MCP access by plan
Watchdog
FreeRead-only tools
6 tools — view servers, alerts, status, diagnostics, playbooks, capabilities
Deployment Bro
$39/moFull access
35+ tools — everything above + diagnostics, playbooks, commands, approvals
Ready to manage servers from your IDE?
Free tier includes 6 read-only tools. No credit card required.
Install in Claude Code:
claude mcp add mttrly --transport http https://api.mttrly.com/mcp