TraceOps AI: Building an AI-Powered Service Investigation Agent with FalkorDB and MCP

Описание и применение

TraceOps AI использует графовую базу FalkorDB, протокол MCP и локальную модель Qwen для быстрого поиска взаимосвязанных данных о сервисах, инцидентах и runbook‑ах, облегчая инженерам расследование сбоев микросервисов.

Задача

Engineers struggle to understand connected operational context when a microservice fails, making it hard to identify impacted services, ownership, incidents, deployments, and runbooks.

Результат

The prototype demonstrates that a graph database combined with MCP‑exposed tools and a local LLM can efficiently surface connected operational evidence, reducing investigation time and improving clarity of root‑cause analysis.

Рабочий процесс

• Receive user question about a service
• Agent interprets request and selects relevant operational data
• MCP tools query FalkorDB for service details, dependencies, ownership, incidents, runbooks, and deployment correlations
• Graph queries traverse relationships, including multi‑hop dependencies
• Agent constructs investigation response using retrieved evidence
• Frontend displays the investigation output to the user

Доказательства

The goal is not to claim that every investigation establishes a definitive root cause. Instead, TraceOps AI aims to help connect relevant evidence and distinguish observed relationships from conclusions that still need verification.

Источник

The prototype includes synthetic operational data representing services, teams, incidents, deployments, and runbooks.

Источник

For this project, I integrated graph investigation capabilities through the Model Context Protocol (MCP).

Источник