Uptimebolt MCP Server

UptimeBolt MCP Server

AI-powered infrastructure monitoring tools for Claude, Claude Code, Cursor, and any MCP-compatible client.

UptimeBolt is an AI-first monitoring platform that groups monitors into logical business services, predicts cascade failures before they happen, and automatically identifies which deploy caused each incident — including the commit, files, and lines of code responsible.

Built by CLM Cloud Solutions in Madrid, Spain.

Why UptimeBolt MCP Server?

Ask your infrastructure questions in natural language. Instead of navigating dashboards, let your AI assistant query real-time monitoring data directly:

• *"Is it safe to deploy right now?"* — get a data-driven answer based on health scores, active incidents, and predictions
• *"What caused the last incident?"* — AI-powered root cause analysis with deploy correlation
• *"Give me an executive summary of the last 24 hours"* — ready for your standup or status report
• *"Show me monitors that are degraded"* — instant filtered view across your infrastructure

Features

• 10 monitoring tools — service status, incidents, predictions, RCA, deploy safety, and more
• Dual transport — stdio (local) + HTTP (remote/CI-CD)
• API key authentication — secure per-request access to your UptimeBolt data
• Works everywhere — Claude Desktop, Claude Code, Cursor, Cline, and any MCP client
• CI/CD ready — deploy safety checks directly in your pipeline

Quick Start

Install globally (recommended)

npm install -g @uptimebolt/mcp-server

Claude Desktop (stdio)

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{

"mcpServers": { "uptimebolt": { "command": "uptimebolt-mcp", "env": { "UPTIMEBOLT_API_KEY": "your-api-key", "UPTIMEBOLT_API_URL": "https://api.uptimebolt.io" } } } }

Or without global install, using npx:

{

"mcpServers": { "uptimebolt": { "command": "npx", "args": ["-y", "--package=@uptimebolt/mcp-server", "uptimebolt-mcp"], "env": { "UPTIMEBOLT_API_KEY": "your-api-key", "UPTIMEBOLT_API_URL": "https://api.uptimebolt.io" } } } }

Claude Code / Cursor

Add to your project's .mcp.json:

{

"mcpServers": { "uptimebolt": { "command": "uptimebolt-mcp", "env": { "UPTIMEBOLT_API_KEY": "your-api-key", "UPTIMEBOLT_API_URL": "https://api.uptimebolt.io" } } } }

Docker (HTTP)

docker run -p 3100:3100 \

-e UPTIMEBOLT_API_URL=https://api.uptimebolt.io \ ghcr.io/clm-cloud-solutions/uptimebolt-mcp-server:latest

Then connect via mcp-remote:

{

"mcpServers": { "uptimebolt": { "command": "npx", "args": ["-y", "mcp-remote", "http://localhost:3100/mcp", "--header", "x-api-key:your-api-key"] } } }

npm (programmatic)

npm install @uptimebolt/mcp-server

import { TOOLS, HANDLERS } from "@uptimebolt/mcp-server";

// TOOLS — MCP tool definitions (10 tools) // HANDLERS — tool handler functions: (args, context?) => Promise

Available Tools

Authentication

Get your API key at app.uptimebolt.io/settings/api-keys.

• stdio mode: Set UPTIMEBOLT_API_KEY environment variable
• HTTP mode: Pass x-api-key header with each request (no startup key required)

CI/CD Integration

Use is_safe_to_deploy as a gate in your deployment pipeline:

curl -X POST http://localhost:3100/mcp \

-H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -H "x-api-key: your-api-key" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "is_safe_to_deploy", "arguments": { "service_name": "my-service" } } }'

The response includes a risk level (low, medium, high), active issues, and a recommendation (proceed, proceed_with_caution, wait_and_monitor).

Configuration

Development

git clone https://github.com/clm-cloud-solutions/uptimebolt-mcp-server.git

cd uptimebolt-mcp-server cp .env.example .env # configure your environment npm install npm run dev # stdio mode npm run dev:http # HTTP mode npm run build # compile TypeScript npm run typecheck # type check without emitting

About UptimeBolt

UptimeBolt is an AI-first SaaS monitoring platform for DevOps teams and SREs. Key capabilities:

• Cascade failure prediction — dependency graph with what-if analysis, downtime cost estimation, and proactive mitigations
• Deploy correlation + RCA 2.0 — automatically correlates GitHub/GitLab deploys with incidents, identifies the responsible commit and files
• AI Copilot — conversational assistant with real-time infrastructure context
• 8 monitor types — HTTP, TCP, DNS, Database, Email, Synthetic, Push, Ping

About CLM Cloud Solutions

CLM Cloud Solutions S.L. is a technology company based in Madrid, Spain, building SaaS products for engineering teams to operate with confidence, speed, and security.

• LinkedIn
• GitHub
• Contact: info@clmcloudsolutions.es

License

MIT