Intelligent Incident Correlation

via “tf-idf-based incident similarity analysis and correlation”

** - MCP server for the incident management platform [Rootly](https://rootly.com/).

Unique: Implements TF-IDF vectorization directly in the MCP server rather than delegating to external ML services, enabling offline incident correlation without API latency. The TextSimilarityAnalyze tool (smart_utils.py) operates on incident data already fetched from Rootly, avoiding round-trip API calls for similarity computation.

vs others: Faster and more cost-effective than cloud-based ML similarity services (e.g., Pinecone, Weaviate) for incident correlation, with no external dependencies or API costs, though less sophisticated than transformer-based embeddings.