Uptimebolt Mcp Server

clm-cloud-solutions/uptimebolt-mcp-server

Connects Claude to UptimeBolt's AI-powered infrastructure monitoring platform. You get 10 tools for querying service health scores, active incidents, cascade failure predictions, and AI root cause analysis that correlates deploys with outages down to specific commits and files. The is_safe_to_deploy tool is built for CI/CD pipelines, returning risk levels based on current health metrics and predictions. Ask natural language questions like "what caused the last incident" or "show me degraded monitors" instead of navigating dashboards. Supports both stdio for local use and HTTP transport for remote deployment scenarios. Built by CLM Cloud Solutions in Madrid for DevOps teams running UptimeBolt monitoring.

GitHub stars: 1
tools: 10
transport: STDIO
last updated: Mar 2, 2026

View on GitHub

Tools

10 tools

Public tool metadata for what this MCP can expose to an agent.

get_service_statusGet the current health status of a service or all services. Returns health score, monitor status, and active incidents.2 params

Get the current health status of a service or all services. Returns health score, monitor status, and active incidents.

Parameters* required

service_idstring

UUID of the service. Omit to get all services.

service_namestring

Name of the service (fuzzy match). Alternative to service_id.

get_predictionsGet active AI predictions for monitors or services. Shows predicted problems with confidence levels.3 params

Get active AI predictions for monitors or services. Shows predicted problems with confidence levels.

Parameters* required

min_confidencenumber

Minimum confidence threshold (0-100). Default: 60.

monitor_idstring

Filter predictions by monitor UUID.

service_idstring

Filter predictions by service UUID.

get_incidentsGet incidents with optional filters. Includes root cause analysis if available.5 params

Get incidents with optional filters. Includes root cause analysis if available.

Parameters* required

hoursnumber

Look back N hours. Default: 24.

include_rcaboolean

Include root cause analysis details. Default: true.

monitor_idstring

Filter incidents by monitor UUID.

service_idstring

Filter incidents by service UUID.

statusstring

Filter by status. 'active' = all non-resolved. Default: active.one of active · resolved · detecting · investigating · identified · resolving

get_monitor_healthGet detailed health information for a specific monitor including response time, uptime, and active predictions.3 params

Get detailed health information for a specific monitor including response time, uptime, and active predictions.

Parameters* required

monitor_idstring

UUID of the monitor.

monitor_namestring

Name of the monitor (fuzzy match). Alternative to monitor_id.

periodstring

Time period for statistics. Default: 24h.one of 1h · 6h · 24h · 7d · 30d

get_deploymentsGet recent deployments and their correlation with incidents. Shows which deploys potentially caused issues.3 params

Get recent deployments and their correlation with incidents. Shows which deploys potentially caused issues.

Parameters* required

hoursnumber

Look back N hours. Default: 24.

include_correlationsboolean

Include incident correlations. Default: true.

service_idstring

Filter deployments by service UUID.

run_root_cause_analysisRun an AI-powered root cause analysis for an incident or service. Analyzes dependencies, cascading failures, and deployment correlations.4 params

Run an AI-powered root cause analysis for an incident or service. Analyzes dependencies, cascading failures, and deployment correlations.

Parameters* required

incident_idstring

UUID of the incident to analyze.

languagestring

Response language. Default: es.one of es · en

service_idstring

UUID of the service to analyze (alternative to incident_id).

tierstring

Analysis depth tier. Default: standard.one of basic · standard · deep · premium

is_safe_to_deployCheck if it's safe to deploy right now based on current service health, active predictions, and recent incidents. Useful for CI/CD pipeline integration.2 params

Check if it's safe to deploy right now based on current service health, active predictions, and recent incidents. Useful for CI/CD pipeline integration.

Parameters* required

service_idstring

UUID of the service to check.

service_namestring

Name of the service (fuzzy match).

get_executive_summaryGet an executive summary of infrastructure health for a time period. Ideal for daily standups, weekly reports, or status updates.2 params

Get an executive summary of infrastructure health for a time period. Ideal for daily standups, weekly reports, or status updates.

Parameters* required

hoursnumber

Period to summarize in hours. Default: 12.

languagestring

Response language. Default: es.one of es · en

get_monitorsList all monitors with optional filtering by status or type. Returns name, URL, operational status, response time, and uptime for each monitor.2 params

List all monitors with optional filtering by status or type. Returns name, URL, operational status, response time, and uptime for each monitor.

Parameters* required

statusstring

Filter by status. 'up/down/degraded' filter by operational status, 'paused/maintenance/active' by admin status. Default: all.one of all · up · down · degraded · paused · maintenance

typestring

Filter by monitor type.one of http · tcp · dns · database · email · synthetic

get_monitor_metricsGet detailed metrics summary for a specific monitor including response time stats, uptime percentage, and error breakdown.2 params

Get detailed metrics summary for a specific monitor including response time stats, uptime percentage, and error breakdown.

Parameters* required

monitor_idstring

UUID of the monitor.

monitor_namestring

Name of the monitor (fuzzy match). Alternative to monitor_id.

Readme

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

View the full README on GitHub

Details

Repository: github.com/clm-cloud-solutions/uptimebolt-mcp-server
Category: Cloud & Infrastructure
Package: @uptimebolt/mcp-server
Transport: STDIO
Registry: MCP registry, active

Related Cloud & Infrastructure MCP servers

View all

Warmth Engine Observatorywarmthengine/warmth-engine-observatoryCoordination Intelligence: AI infrastructure coordination dynamics across geopolitical blocs1stars

Nexusaddozhang/nexus-mcp-serverQuery Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts1stars

SQL Server MCP (macOS)tharanabope/sql-mcp-mac-windowsSQL Server MCP with RAG capabilities for macOS (Docker SQL Server support)0stars

WhisperGraphwhisper-sec/whisper-graph-mcpThe internet's infrastructure graph for AI agents - 46B nodes and edges, free trial via 2 HTTP calls1stars

Kubeleashkubeleash/kubeleashKubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.1stars

BorealHostalainsvrd/borealhost-mcpAgent-native web hosting — deploy sites, manage DNS, register domains, scale infrastructure0stars