incident-mcp
{"type": "text"}# incident-mcp
Servidor Python MCP (Model Context Protocol) que ayuda en la detección de incidentes (detection) → análisis (analysis). Detecta anomalías en series temporales de métricas y agrupa correlaciones para ofrecer posibles causas raíz y acciones recomendadas.
Los dos backends comparten un único contrato de herramientas (tool contract):
Servidor | Backend | Propósito |
| Datos sintéticos integrados (deterministas) | Desarrollo, demostración y pruebas de regresión sin VM |
| API HTTP real de VictoriaMetrics | Análisis de incidentes operativos/medidos |
Como las firmas de las herramientas de ambos servidores son 100 % idénticas, puede desarrollar el flujo de trabajo con el mock y cambiar a la VM real sin interrupciones.
Arquitectura
incident_mcp/
├── core/ # 백엔드 무관 공통 로직 (순수 함수 → 테스트 용이)
│ ├── models.py # Pydantic: Anomaly, IncidentAnalysis, Series ...
│ ├── datasource.py # Protocol(인터페이스) — VM/Mock이 구현
│ ├── detection.py # 이상탐지: zscore · spike · trend · threshold
│ └── analysis.py # 상관분석 + 근본원인 휴리스틱
├── datasources/
│ ├── mock_ds.py # 재현 가능한 합성 메트릭 + 주입된 인시던트 시나리오
│ └── vm_ds.py # VictoriaMetrics(Prometheus 호환) HTTP 클라이언트
├── servers/
│ ├── mock_server.py # B: mock 데이터소스 주입
│ └── vm_server.py # A: VictoriaMetrics 데이터소스 주입
└── tools.py # 공통 MCP 도구 4종 (두 서버가 공유)4 herramientas MCP
Herramienta | Descripción |
| Catálogo de métricas disponibles |
| Consulta de series temporales sin procesar (verificación/depuración) |
| Ejecutar detección de anomalías (zscore/spike/trend) |
| Detección y análisis en un solo paso (posibles causas raíz + acciones recomendadas) |
Related MCP server: MCP Server for vmanomaly
Inicio rápido
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
# 단위 테스트
pytest -q
# mock 서버로 종단(E2E) 데모 — mock 2개 시나리오 + 실제 VM
python examples/e2e_client.pyDocumentación (paso a paso)
Métodos de detección de anomalías (resumen)
Método | Patrón detectado | Ejemplo de incidente |
| Valor puntual que se desvía mucho de la media | Pico momentáneo |
| Tasa de cambio abrupta respecto al período anterior | Aumento repentino de la tasa de error |
| Aumento/disminución monótona gradual | Fuga de memoria (no se detecta con zscore/spike) |
| Violación de umbral absoluto | Exceso del límite de SLA |
💡 Los patrones de «fuga lenta», como las fugas de memoria, no se detectan con los métodos basados en valores instantáneos (zscore/spike), por lo que se ha añadido un detector
trendbasado en la pendiente de regresión. — ver step2
Licencia
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceA comprehensive, AI-powered performance analysis and monitoring platform for OpenShift/Kubernetes clusters. This project provides Model Context Protocol (MCP) servers for analyzing etcd, network, and OVN-Kubernetes components with deep performance insights, automated root cause analysis, and actionable recommendations.1Apache 2.0
- Alicense-qualityAmaintenanceMCP server that integrates with VictoriaMetrics vmanomaly API to enable AI-assisted anomaly detection, model management, and configuration generation.9Apache 2.0
- AlicenseAqualityCmaintenanceExposes an observability REST API as MCP tools, enabling incident investigation through automated correlation of deploys with errors, log and metrics queries.6MIT
- FlicenseAqualityCmaintenanceAI-powered incident management MCP server that enables investigation, root cause analysis, and response actions for production incidents using mocked data for demo purposes.8
Related MCP Connectors
Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.
Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.
Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yoojung2/incident-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server