senior-copilot-mcp-rag-assignment

senior-copilot-mcp-rag-assignment

Enables alarm investigation through MCP tools for asset search, metadata lookup, alarm retrieval, summarization, priority scoring, and operator recommendations, with RAG-backed evidence from procedure documents.

Category
Visit Server

README

Alarm Investigation and Procedure Guidance Copilot

This repository implements an evidence-backed alarm investigation workflow using:

  • a FastAPI-based Alarm Management API simulator
  • a candidate-developed MCP server exposing alarm operations as typed tools
  • a Streamlit GUI that discovers and invokes MCP tools
  • a document RAG workflow over alarm procedures and troubleshooting guides

Main capabilities

  • Natural-language alarm investigation requests
  • MCP tool discovery and invocation for asset search, metadata lookup, alarm retrieval, summaries, priority scoring, and recommendations
  • RAG-backed evidence using operating procedures and maintenance documents
  • Tool trace and raw response inspection in the UI

Technology stack

  • Python 3.11+
  • FastAPI
  • Streamlit
  • scikit-learn for TF-IDF retrieval
  • pytest

MCP server

The MCP server is implemented under apps/mcp_server and exposes the following tools:

  • asset_search
  • asset_metadata
  • alarm_retrieval
  • alarm_summary
  • priority_score
  • operator_recommendations

Start the MCP server independently:

uvicorn apps.mcp_server.main:app --host 0.0.0.0 --port 9000

Alarm API backend

Start the backend simulator:

uvicorn apps.backend.main:app --host 0.0.0.0 --port 8000

Streamlit UI

Start the GUI:

streamlit run apps/frontend/app.py

RAG workflow

Documents are stored under rag/documents and ingested through the existing TF-IDF index in apps/backend/rag.py.

Tests

python -m pytest -q

Configuration

Copy .env.example and adjust values as needed.

Architecture summary

See docs/architecture.md and docs/architecture-diagram.svg.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured