Skip to main content
Glama
deenesjakoruzh
yoojung2

incident-mcp

by yoojung2
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

incident-mcp

Python-MCP-Server (Model Context Protocol) zur Unterstützung von Incident-Erkennung (Detection) → Analyse (Analysis). Er erkennt Anomalien in Metrik-Zeitreihen, bündelt Korrelationen und liefert Root-Cause-Kandidaten sowie empfohlene Maßnahmen.

Ein Tool-Vertrag wird von zwei Backends geteilt:

Server

Backend

Zweck

mock-incident-mcp

Integrierte synthetische Daten (deterministisch)

Entwicklung, Demo und Regressionstests ohne VM

vm-incident-mcp

Echte VictoriaMetrics-HTTP-API

Betriebs-/Echtzeit-Incident-Analyse

Da die Tool-Signaturen beider Server zu 100 % identisch sind, kann ein mit dem Mock entwickelter Workflow ohne Unterbrechung auf die echte VM umgestellt werden.

Architektur

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 MCP-Tools

Tool

Beschreibung

list_metrics

Katalog verfügbarer Metriken

fetch_series

Roh-Zeitreihenabfrage (Verifikation/Debugging)

detect_anomalies

Anomalieerkennung ausführen (zscore/spike/trend)

analyze_incident

Erkennung→Analyse in einem Schritt (Root-Cause-Kandidaten + empfohlene Maßnahmen)

Related MCP server: MCP Server for vmanomaly

Schnellstart

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.py

Dokumentation (Schritt für Schritt)

Anomalieerkennungsmethoden (Zusammenfassung)

Methode

Erkanntes Muster

Beispiel-Incident

zscore

Momentanwerte stark abweichend vom Mittelwert

Momentaner Spike

spike

Abrupte Änderungsrate gegenüber dem vorherigen Intervall

Plötzlicher Anstieg der Fehlerrate

trend

Allmählicher monotoner Anstieg/Rückgang

Speicherleck (mit zscore/spike nicht erkennbar)

threshold

Verletzung absoluter Schwellenwerte

Überschreitung des SLA-Limits

💡 Muster, die „langsam lecken“ – wie Speicherlecks – werden von momentwertbasierten Methoden (zscore/spike) nicht erkannt. Deshalb gibt es einen separaten regressionsbasierten trend-Detektor. – Siehe Schritt 2

Lizenz

MIT

This server cannot be installed

A
license - permissive license
-
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

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

  • OCP Performance Analyzer MCP by openshift-eng

    OCP Performance Analyzer MCPofficial

    openshift-eng
    A
    license
    -
    quality
    D
    maintenance
    A 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.
    1
    Apache 2.0

  • incident-commander-mcp

    hashirR786
    F
    license
    A
    quality
    C
    maintenance
    AI-powered incident management MCP server that enables investigation, root cause analysis, and response actions for production incidents using mocked data for demo purposes.
    8

View all related MCP servers

Related MCP Connectors

  • Fixzi — MCP & API Schema Drift Monitor

    Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.

  • Agentic Platform

    Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.

  • mockmcp

    Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.

View all MCP Connectors

Latest Blog Posts

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