KPI Monitoring MCP Server
MCP server providing data analytics tools for AI agents to load, clean, analyze data, generate charts and dashboards.
README
🚀 KPI Monitoring System — Run Guide
Prérequis
- Python 3.10+
- pip
Installation
# 1. Cloner le repo
git clone <url-du-repo>
cd project
# 2. Installer les dépendances
pip install -r requirements.txt
# 3. Configurer la clé API
cp .env.example .env
# Éditer .env et mettre ta clé Anthropic :
# ANTHROPIC_API_KEY=sk-ant-xxxxxxx
Lancement
Terminal 1 — MCP Server (port 8000)
uvicorn app.mcp.server:app --port 8000 --reload
Terminal 2 — API principale (port 8001)
uvicorn app.main:app --port 8001 --reload
Tester le système
# Test 1 : MCP Server opérationnel ?
curl http://localhost:8000/health
# Test 2 : Lister les outils disponibles
curl http://localhost:8000/tools
# Test 3 : Vérifier les permissions d'un agent
curl http://localhost:8000/permissions/data_engineer
# Test 4 : Lancer un pipeline complet
curl -X POST http://localhost:8001/run/start \
-F "file=@online_retail_raw.csv" \
-F "objective=Analyse les KPIs de ventes et génère un dashboard"
# Test 5 : Voir les logs d'un run
curl http://localhost:8001/run/run_20241201_120000/logs
Structure des fichiers produits
runs/
run_20241201_120000/
metadata.json ← info du run
decisions.jsonl ← décisions des agents
tool_calls.jsonl ← appels MCP
artifacts/
cleaned_data.csv ← produit par Data Engineer
insights.json ← KPIs produits par Data Scientist
report.html ← rapport final produit par Reporter
charts/
ca_mensuel.html ← graphiques produits par BI Agent
top_pays.html
repartition.html
dashboard.html ← dashboard assemblé par BI Agent
Responsabilités par personne
| Fichier | Codé par |
|---|---|
| app/mcp/server.py | P1 |
| app/orchestrator/engine.py | P1 |
| app/agents/devops_agent.py | P1 |
| app/storage/artifact_store.py | P1 |
| app/tools/load_dataset.py | P2 |
| app/tools/quality_check.py | P2 |
| app/tools/clean_data.py | P2 |
| app/tools/run_analysis.py | P2 |
| app/agents/data_engineer.py | P2 |
| app/agents/data_scientist.py | P2 |
| app/tools/generate_chart.py | P3 |
| app/tools/publish_dashboard.py | P3 |
| app/agents/bi_agent.py | P3 |
| app/tools/compile_report.py | P4 |
| app/agents/reporter.py | P4 |
| app/main.py (UI backend) | P4 |
| #� �t�e�s�t�-�p�f�a� | |
| � | |
| � |
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.