{
  "markdown": "# UptimeBolt MCP Server\n\nAI-powered infrastructure monitoring tools for [Claude](https://claude.ai), [Claude Code](https://claude.ai/code), [Cursor](https://cursor.com), and any MCP-compatible client.\n\n[UptimeBolt](https://uptimebolt.com) 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.\n\nBuilt by [CLM Cloud Solutions](https://clmcloudsolutions.es) in Madrid, Spain.\n\n## Why UptimeBolt MCP Server?\n\nAsk your infrastructure questions in natural language. Instead of navigating dashboards, let your AI assistant query real-time monitoring data directly:\n\n- *\"Is it safe to deploy right now?\"* — get a data-driven answer based on health scores, active incidents, and predictions\n- *\"What caused the last incident?\"* — AI-powered root cause analysis with deploy correlation\n- *\"Give me an executive summary of the last 24 hours\"* — ready for your standup or status report\n- *\"Show me monitors that are degraded\"* — instant filtered view across your infrastructure\n\n## Features\n\n- **10 monitoring tools** — service status, incidents, predictions, RCA, deploy safety, and more\n- **Dual transport** — stdio (local) + HTTP (remote/CI-CD)\n- **API key authentication** — secure per-request access to your UptimeBolt data\n- **Works everywhere** — Claude Desktop, Claude Code, Cursor, Cline, and any MCP client\n- **CI/CD ready** — deploy safety checks directly in your pipeline\n\n## Quick Start\n\n### Install globally (recommended)\n\n```bash\nnpm install -g @uptimebolt/mcp-server\n```\n\n### Claude Desktop (stdio)\n\nAdd to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"uptimebolt\": {\n      \"command\": \"uptimebolt-mcp\",\n      \"env\": {\n        \"UPTIMEBOLT_API_KEY\": \"your-api-key\",\n        \"UPTIMEBOLT_API_URL\": \"https://api.uptimebolt.io\"\n      }\n    }\n  }\n}\n```\n\nOr without global install, using npx:\n\n```json\n{\n  \"mcpServers\": {\n    \"uptimebolt\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"--package=@uptimebolt/mcp-server\", \"uptimebolt-mcp\"],\n      \"env\": {\n        \"UPTIMEBOLT_API_KEY\": \"your-api-key\",\n        \"UPTIMEBOLT_API_URL\": \"https://api.uptimebolt.io\"\n      }\n    }\n  }\n}\n```\n\n### Claude Code / Cursor\n\nAdd to your project's `.mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"uptimebolt\": {\n      \"command\": \"uptimebolt-mcp\",\n      \"env\": {\n        \"UPTIMEBOLT_API_KEY\": \"your-api-key\",\n        \"UPTIMEBOLT_API_URL\": \"https://api.uptimebolt.io\"\n      }\n    }\n  }\n}\n```\n\n### Docker (HTTP)\n\n```bash\ndocker run -p 3100:3100 \\\n  -e UPTIMEBOLT_API_URL=https://api.uptimebolt.io \\\n  ghcr.io/clm-cloud-solutions/uptimebolt-mcp-server:latest\n```\n\nThen connect via `mcp-remote`:\n\n```json\n{\n  \"mcpServers\": {\n    \"uptimebolt\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"http://localhost:3100/mcp\", \"--header\", \"x-api-key:your-api-key\"]\n    }\n  }\n}\n```\n\n### npm (programmatic)\n\n```bash\nnpm install @uptimebolt/mcp-server\n```\n\n```typescript\nimport { TOOLS, HANDLERS } from \"@uptimebolt/mcp-server\";\n\n// TOOLS — MCP tool definitions (10 tools)\n// HANDLERS — tool handler functions: (args, context?) => Promise<result>\n```\n\n## Available Tools\n\n| Tool | Description |\n|------|-------------|\n| `get_service_status` | Health status of business services with health score (0-100), monitor breakdown, and active incidents |\n| `get_monitors` | List all monitors with operational status, response time, and uptime percentage |\n| `get_monitor_health` | Detailed health for a specific monitor including response time trends and active predictions |\n| `get_monitor_metrics` | Response time stats (avg, p95, p99), uptime percentage, and error breakdown |\n| `get_incidents` | Active and resolved incidents with optional AI root cause analysis details |\n| `get_predictions` | AI predictions for upcoming issues with confidence levels and predicted impact |\n| `get_deployments` | Recent deployments with automatic incident correlation (GitHub/GitLab) |\n| `run_root_cause_analysis` | AI-powered RCA using multi-model analysis (Claude, GPT) with deploy correlation |\n| `is_safe_to_deploy` | CI/CD deploy safety check based on health scores, predictions, and active incidents |\n| `get_executive_summary` | Infrastructure health summary for standups, weekly reports, or status updates |\n\n## Authentication\n\nGet your API key at [app.uptimebolt.io/settings/api-keys](https://app.uptimebolt.io/settings/api-keys).\n\n- **stdio mode**: Set `UPTIMEBOLT_API_KEY` environment variable\n- **HTTP mode**: Pass `x-api-key` header with each request (no startup key required)\n\n## CI/CD Integration\n\nUse `is_safe_to_deploy` as a gate in your deployment pipeline:\n\n```bash\ncurl -X POST http://localhost:3100/mcp \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Accept: application/json, text/event-stream\" \\\n  -H \"x-api-key: your-api-key\" \\\n  -d '{\n    \"jsonrpc\": \"2.0\",\n    \"id\": 1,\n    \"method\": \"tools/call\",\n    \"params\": {\n      \"name\": \"is_safe_to_deploy\",\n      \"arguments\": { \"service_name\": \"my-service\" }\n    }\n  }'\n```\n\nThe response includes a risk level (`low`, `medium`, `high`), active issues, and a recommendation (`proceed`, `proceed_with_caution`, `wait_and_monitor`).\n\n## Configuration\n\n| Variable | Description | Default |\n|----------|-------------|---------|\n| `UPTIMEBOLT_API_KEY` | Your UptimeBolt API key | (required for stdio) |\n| `UPTIMEBOLT_API_URL` | UptimeBolt API base URL | `http://localhost:3200` |\n| `MCP_HTTP_PORT` | HTTP server port | `3100` |\n| `NODE_ENV` | Environment (`production` disables console logs) | `development` |\n| `LOG_LEVEL` | Log level (error, warn, info, debug) | `debug` (dev) / `info` (prod) |\n\n## Development\n\n```bash\ngit clone https://github.com/clm-cloud-solutions/uptimebolt-mcp-server.git\ncd uptimebolt-mcp-server\ncp .env.example .env          # configure your environment\nnpm install\nnpm run dev          # stdio mode\nnpm run dev:http     # HTTP mode\nnpm run build        # compile TypeScript\nnpm run typecheck    # type check without emitting\n```\n\n## About UptimeBolt\n\n[UptimeBolt](https://uptimebolt.com) is an AI-first SaaS monitoring platform for DevOps teams and SREs. Key capabilities:\n\n- **Cascade failure prediction** — dependency graph with what-if analysis, downtime cost estimation, and proactive mitigations\n- **Deploy correlation + RCA 2.0** — automatically correlates GitHub/GitLab deploys with incidents, identifies the responsible commit and files\n- **AI Copilot** — conversational assistant with real-time infrastructure context\n- **8 monitor types** — HTTP, TCP, DNS, Database, Email, Synthetic, Push, Ping\n\n## About CLM Cloud Solutions\n\n[CLM Cloud Solutions S.L.](https://clmcloudsolutions.es) is a technology company based in Madrid, Spain, building SaaS products for engineering teams to operate with confidence, speed, and security.\n\n- [LinkedIn](https://www.linkedin.com/company/clm-cloud-solutions/)\n- [GitHub](https://github.com/clm-cloud-solutions)\n- Contact: info@clmcloudsolutions.es\n\n## License\n\nMIT\n",
  "bytes": 7147,
  "sha": "0abe79084b299163513ccc8da0c5005373bab92b037a0f9e639aa47dd6c9084f",
  "repo_slug": "clm-cloud-solutions/uptimebolt-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_clm_cloud_solutions_uptimebolt_e82d89e4/readme"
}