Provides AI-powered analysis of exceptions using Azure OpenAI's language models, enabling intelligent reasoning and categorization of stack traces and error data.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@exception-mcp-server find similar exceptions to RuntimeError: Connection timeout"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AI-powered exception analysis for operations teams
# 1. Install dependencies
pip install -r requirements.txt
# 2. Configure credentials
# Edit config.yaml and paste your Azure OpenAI endpoint and API key:
# azure_openai:
# endpoint: "https://your-resource.openai.azure.com/"
# api_key: "your-api-key-here"
# 3. Run tests
python test_framework.py
# 4. Ingest data
python ingest.py
# 5. Launch UI
streamlit run streamlit_app.pyRelated MCP server: otel-mcp-server
See FRAMEWORK_README.md for complete documentation including:
Configuration guide
Testing procedures
Usage examples
Adaptation for other projects
Troubleshooting
python test_framework.pyExpected: 5/7 tests pass (2 expected failures: ChromaDB install, Azure credentials)
├── config.yaml # Configuration
├── llm_client.py # Azure OpenAI client
├── stacktrace_parser.py # Parse stack traces
├── vector_store.py # ChromaDB wrapper
├── server.py # MCP server
├── streamlit_app.py # UI
├── ingest.py # Load data into vector DB
├── test_framework.py # Test suite
├── data/
│ └── exceptions.csv # Exception data (100 samples)
└── FRAMEWORK_README.md # Complete documentationVector similarity search using ChromaDB
AI analysis with Azure OpenAI
Simple architecture that works across projects
Comprehensive tests included
Copy-paste schema - no manual definitions
Framework is production-ready. Run tests and start analyzing exceptions! 🎯
This server cannot be deployed
Track errors, manage performance alerts, and configure dashboards and monitors
AI agent run monitoring with incident replay and SLA receipts.
AI-powered incident management and server monitoring via MCP.
Read-only triage for n8n, MCP, webhook, and AI agent workflow production failures.
