Which integrations are available for this server?

Allows sending automated email reports via Gmail SMTP. Integrates with NVIDIA NIM API to generate AI insights from sales data using free inference credits. Creates interactive HTML dashboards using Plotly for data visualization.

How do I use AI Sales Analytics MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@AI Sales Analytics MCP Server analyze my latest sales data and email the report" 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 Sales Analytics MCP Server

by Abhishek-Maheshwari-778

Overview Schema Source Related Servers Discussions Admin

Python

Local

⚡ AI Sales Analytics — MCP Automation System

No Power BI Login. No Manual Work. Just drop a CSV and AI does everything.

🎯 What This Does

You Do	System Does Automatically
Drop a `.csv` file	Detects it instantly
Nothing	Cleans & validates data
Nothing	AI generates business insights
Nothing	Creates interactive HTML dashboard
Nothing	Exports professional PDF report
Nothing	Emails report to anyone

Related MCP server: Sales Dashboard

🤖 Multi-Model AI Fallback Chain

The system automatically tries each AI provider and falls back if unavailable:

1. 🟢 NVIDIA NIM   → Free, 1000 credits (nvapi-...)
2. 🟢 Groq         → Free, no credit card (gsk_...)
3. 🟡 DeepSeek     → Near-free credits (sk-...)
4. 🔵 Rule-Based   → 100% offline, always works

No internet? No API keys? → Rule-based insights still work perfectly!

🚀 Quick Start (5 Minutes)

Step 1 — Install Dependencies

pip install -r requirements.txt

Step 2 — Generate Sample Data (or use your own CSV)

python generate_sample_data.py

Step 3 — Add API Keys (Optional but recommended)

Copy .env.example → .env and fill in your keys:

copy .env.example .env
# Edit .env with your keys

Step 4 — Run the Pipeline!

# Option A: Run once on existing data
python main.py

# Option B: Watch folder (auto-trigger on CSV drop)
python watcher.py

# Option C: Chat with AI agent
python agent.py

🔑 How to Get FREE API Keys

NVIDIA NIM (Recommended — Best free models)

Go to → https://build.nvidia.com
Click Login / Sign Up (free account)
Go to API Keys → Create API Key
Copy key (starts with nvapi-)
Add to .env: NVIDIA_API_KEY=nvapi-xxxxx

Free tier: 1000 inference credits. Model: meta/llama-3.3-70b-instruct

Groq (Fastest — No credit card)

Go to → https://console.groq.com
Sign up with Gmail or GitHub
Go to API Keys → Create API Key
Copy key (starts with gsk_)
Add to .env: GROQ_API_KEY=gsk_xxxxx

Free tier: Generous rate limits, no card needed. Model: llama-3.3-70b-versatile

DeepSeek (Very cheap)

Go to → https://platform.deepseek.com
Sign up → Go to API Keys → Create
Add to .env: DEEPSEEK_API_KEY=sk-xxxxx

📧 Email Setup (Gmail)

Go to myaccount.google.com
Security → 2-Step Verification (enable)
Security → App passwords → Select "Mail" → Generate
Copy 16-char password (e.g. abcd efgh ijkl mnop)

Add to .env:

EMAIL_SENDER=you@gmail.com
EMAIL_PASSWORD=abcdefghijklmnop
EMAIL_RECEIVER=boss@company.com

📁 Project Structure

AI-PowerBI-MCP-Automation/
│
├── 📂 data/
│   ├── sales.csv              ← Your input CSV
│   └── cleaned_sales.csv      ← Auto-generated
│
├── 📂 reports/                ← All outputs here
│   ├── dashboard.html         ← 🌐 Open in browser!
│   ├── report.pdf             ← 📄 Professional report
│   └── insights.json          ← Raw KPI data
│
├── 📂 incoming/               ← DROP CSV HERE for auto-trigger
│
├── 📂 src/
│   ├── ai_engine.py           ← Multi-model AI fallback
│   ├── clean_data.py          ← Data cleaning
│   ├── insights.py            ← KPI + AI insights
│   ├── dashboard.py           ← HTML dashboard (replaces Power BI)
│   ├── export_pdf.py          ← PDF report
│   └── send_email.py          ← Email automation
│
├── 📂 mcp_server/
│   └── server.py              ← MCP server (AI agent tools)
│
├── main.py                    ← Run full pipeline
├── watcher.py                 ← Folder auto-watcher
├── agent.py                   ← Chat interface
├── generate_sample_data.py    ← Generate test data
├── config.py                  ← All settings & API keys
├── .env.example               ← Key template
└── requirements.txt

💬 Agent Chat Examples

python agent.py

You → analyze today's sales
🤖  → Running FULL PIPELINE...
     ✅ Data cleaned (1200 rows)
     ✅ AI insights via NVIDIA NIM
     ✅ Dashboard created
     ✅ PDF exported
     ✅ Email sent

You → show dashboard
🤖  → Opening dashboard in browser...

You → status
🤖  → Total Sales: ₹45,23,400  |  Profit: 18.3%
     Top Product: Laptop Pro X  |  Region: West

You → send report
🤖  → Email delivered to boss@company.com ✓

🔌 MCP Server (For AI Agents like Claude)

Add to your Claude Desktop mcp_settings.json:

{
  "mcpServers": {
    "ai-sales-analytics": {
      "command": "python",
      "args": ["C:/path/to/mcp_server/server.py"]
    }
  }
}

Available MCP Tools:

Tool	Description
`run_full_pipeline`	Run everything end-to-end
`clean_data`	Clean CSV file
`generate_insights`	Get AI insights + KPIs
`create_dashboard`	Build HTML dashboard
`export_pdf`	Generate PDF report
`send_email`	Email the report
`get_status`	Check system status

📊 Dashboard Preview

The HTML dashboard includes:

💰 KPI Cards (Sales, Profit, Orders, Avg Order Value)
📈 Monthly Sales Trend (interactive line chart)
🏅 Top 10 Products (horizontal bar chart)
🗺️ Region-wise Sales (donut chart)
📦 Category Breakdown (bar chart)
🧠 AI-Generated Insights Panel

Opens in Chrome/Edge/Firefox — NO Power BI, NO Microsoft login!

🎓 Resume Description

AI-Powered Sales Analytics Automation using MCP Server

• Built an end-to-end agentic AI pipeline using Python, MCP Server, and multi-model AI
• Implemented intelligent fallback: NVIDIA NIM → Groq → DeepSeek → Rule-based insights
• Automated CSV ingestion, data cleaning, KPI generation, and interactive dashboard creation
• Replaced Power BI with custom Plotly HTML dashboards (no login required)
• Integrated watchdog folder monitoring for zero-touch automation
• Delivered PDF reports and email notifications via SMTP automation
• Exposed pipeline as MCP tools enabling AI agents to analyze data through natural language

📞 Tech Stack

Layer	Technology
Data	Python + Pandas
AI	NVIDIA NIM / Groq / DeepSeek / Rule-based
Dashboard	Plotly (interactive HTML)
PDF	ReportLab
Email	SMTP (Gmail)
Automation	Watchdog
AI Protocol	MCP (Model Context Protocol)

Built with ❤️ — No Power BI login required. Works 100% locally.

🌐 Web Interface (Addon)

A new interactive web interface is available!

Run python app.py
Open http://localhost:8000
Enjoy Drag & Drop uploads, Multi-Domain support (Sales, Health, Trading), and automatic saving of API keys.

🟡 Power BI Integration (.pbids)

The pipeline now automatically generates an optimized .pbids file. Double-clicking this file opens Power BI instantly connected to your clean data, allowing you to bypass Power Query entirely.

👨‍💻 About the Developers

Abhishek Maheshwari (Developer): Engineered this pipeline to showcase advanced AI agentic workflows, multi-model LLMs, and Python data engineering.
Harshit Varshney (Mentor): Google, IBM, and HubSpot Certified. LinkedIn Profile

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Phos Analytics Engine
io.github.albermm
Sales analytics, ML forecasting, customer segmentation, and trend analysis.
Finance Research & Data Marketing
2
DocuQueue MCP B
io.github.dvcoolarun
Generate PDFs from templates via AI chat. Works with Claude, ChatGPT, Cursor, and any MCP client.
Workplace & Productivity Content Management Systems
1111
Handiworks A
io.github.Lukehal
MCP tools for AI agents: render URLs to image/PDF, check link health, convert HTML/CSV/JSON.
Browser Automation Developer Tools Agent Orchestration
32
analytics-engine
nz.phos
AI analytics — sales analysis, ML forecasting, customer segmentation.
Research & Data Finance Marketing
2

Related MCP Servers

MCP CSV Sales Analyzer
Research & Data AI & Machine Learning
idobe2
F
license
Not graded
quality
D
maintenance
Analyzes sales CSV data to filter records, compute KPIs, and generate AI-powered insights and recommendations using OpenAI.
Updated 8 months ago (2026-01-05 12:18 UTC)
-
Sales Dashboard
Finance Data Visualization
DACdigital
A
license
Not graded
quality
B
maintenance
Enables interactive sales data exploration within Claude through a dynamic dashboard with filterable charts and tables.
Updated 3 months ago (2026-06-23 08:36 UTC)
MIT
mcp-data-summary
Data Visualization Research & Data
Geyo33
F
license
A
quality
D
maintenance
Enables LLMs to generate visual summary reports from CSV datasets using MCP Resources, Tools, and Prompts, without exposing raw data to the model.
Updated 5 months ago (2026-04-01 10:07 UTC)
10
-
PDF Report Generator MCP
Data Visualization AI & Machine Learning
yestharanthony-png
F
license
Not graded
quality
B
maintenance
Generates professional PDF reports with live Power BI dashboards, charts, and insights from plain-text prompts containing CSV data.
Updated 2 months ago (2026-07-09 09:28 UTC)
-

Appeared in Searches

A tool for creating visualizations from reports