README.md

metadata

title: MCP Server Odoo - First AI-Native ERP Integration
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.33.0
app_file: app.py
pinned: false
license: mit
tags:
  - mcp-server-track
  - odoo
  - ai
  - crm
  - sales

🚀 MCP Server Odoo: Where AI Meets Enterprise ERP

🏆 MCP Hackathon Participation - Track: MCP Server
Innovation: First native MCP server for Odoo ERP enabling AI to directly interact with critical business data

🎯 Hackathon Challenge Solved

Problem: Companies use Odoo ERP but AI has no direct access
Innovative Solution: An MCP server that transforms Odoo into a data source accessible to AI via Model Context Protocol

🌟 Why is this revolutionary?

• ✨ First MCP server for Odoo - Connects AI directly to ERP data
• 🔥 Integrated Gradio interface - Live demo + MCP server in single deployment
• 🚀 Production ready - Native CRM/Sales tools + ML analysis via Modal
• 🎯 MCP Server Track - Exposes 15+ Odoo tools via Model Context Protocol

🤖 MCP Innovation: AI Understands Your Business

# Claude can now do this automatically:
"Analyze my leads this week and suggest priority actions"
"Create a Q4 sales report with ML predictions"
"Identify at-risk customers in my CRM pipeline"

Before: Manual data extraction → Analysis → Action
After: AI directly accesses Odoo and provides actionable insights

📊 Hackathon Architecture

🎯 MCP Client (Claude/Cursor)
    ↕ Model Context Protocol
🌐 Gradio Interface + MCP Server  
    ↕ XML-RPC  
💼 Odoo ERP (CRM/Sales/Data)
    ↕ REST API
🚀 Modal ML (Predictive Analytics)

🔧 Exposed MCP Features

🎪 Gradio Interface - Interactive Demo

• Live demo on HuggingFace Spaces
• Real-time testing of MCP tools
• User-friendly interface for non-developers

🤖 MCP Server - 15 exposed tools

# CRM MCP Tools
- get_crm_statistics()           # Real-time pipeline stats
- analyze_leads_advanced()       # AI lead analysis  
- monitor_crm_performance()      # KPI monitoring
- search_leads_by_criteria()     # Smart search

# Sales MCP Tools  
- get_sales_statistics()         # Sales metrics
- analyze_quotations_advanced()  # AI quote analysis
- send_quotation_email()         # Personalized emails
- predict_sales_success()        # ML predictions

🚀 Modal ML - Cloud Computing

• Predictive analytics: Automatic lead scoring
• Customer clustering: Smart segmentation
• Sales forecasting: Advanced ML models

🚀 Instant Demo

HuggingFace Link: Live Interface

Claude Desktop Configuration (1 minute)

{
  "mcpServers": {
    "gradio-odoo": {
      "command": "npx",
      "args": [
        "mcp-remote", 
        "https://aktraiser-mcp-server-odoo.hf.space/gradio_api/mcp/sse"
      ]
    }
  }
}

Result: Claude instantly accesses your Odoo data!

🎖️ Hackathon Strengths

✅ Technical Innovation

• MCP Server Track: Complete protocol implementation
• SSE Transport: Real-time streaming for AI
• Gradio MCP: First functional MCP-Gradio wrapper

✅ Business Impact

• Enterprise Ready: Compatible with all Odoo (SaaS/On-premise)
• Immediate ROI: CRM/Sales analysis automation
• Scalability: Cloud-native architecture with Modal

✅ Developer Experience

• 1-click deployment: HuggingFace Spaces ready
• Complete documentation: Step-by-step guides
• Integrated tests: Automatic validation

📁 Project Architecture

MCP_server_Odoo/
├── 🤖 app.py                      # Gradio Interface + MCP Server
├── ⚙️ config.py                   # Secure Odoo configuration
├── 🔧 crm_gradio_tools.py         # 8 CRM tools for MCP
├── 💼 sales_gradio_tools.py       # 7 Sales tools for MCP  
├── 🚀 modal_gradio_wrapper.py     # Modal Cloud interface
├── 🧠 modal_ml_analysis.py        # Predictive ML analysis
├── 📋 requirements.txt            # Optimized Python stack
└── 📖 README.md                   # Hackathon documentation

🛠️ Express Installation (< 5 min)

Option 1: HuggingFace Spaces (Recommended)

1. Fork the space: aktraiser/mcp-server-odoo
2. Configure your Odoo credentials in the interface
3. Copy the SSE URL into Claude Desktop

Option 2: Local

git clone https://github.com/[your-username]/MCP_server_Odoo
cd MCP_server_Odoo
pip install -r requirements.txt
python app.py

💡 Revolutionary Use Cases

🎯 For Sales Managers

"Claude, analyze my Q1 opportunities and identify at-risk deals"
→ AI accesses Odoo, analyzes 200+ deals, outputs actionable insights

🎯 For Executives

"Predict our Q2 revenue based on current pipeline"
→ AI combines Odoo data + Modal ML → Accurate forecasts

🎯 For Developers

# AI can now code directly with your Odoo data
leads = await mcp_call("search_leads_by_criteria", {"stage": "qualified"})
analysis = await mcp_call("analyze_leads_advanced", {"leads": leads})

🌟 Unique MCP Innovation

What didn't exist before:

• ❌ No MCP server for Odoo
• ❌ AI disconnected from ERP data
• ❌ Time-consuming manual analysis

What our MCP server brings:

• ✅ First integration AI ↔ Odoo native
• ✅ 15 business tools ready to use
• ✅ Live demo functional on HuggingFace
• ✅ Scalable architecture with Modal ML

🎪 Demo Scenarios

Scenario 1: Smart CRM Analysis

curl -X POST "https://aktraiser-mcp-server-odoo.hf.space/gradio_api/mcp/sse" \
  -d '{"method": "tools/call", "params": {"name": "get_crm_statistics"}}'

Scenario 2: ML Sales Prediction

# Via Claude Desktop + MCP
"Use Modal ML to predict which leads will convert this week"
→ AI orchestrates Odoo + Modal automatically

🏆 Why Vote for Us?

Innovation Impact

• 🥇 First Odoo MCP server in the world
• 🥇 First functional Gradio-MCP wrapper
• 🥇 1-click deployment on HuggingFace Spaces

Business Impact

• 💰 Immediate ROI: Business analysis automation
• ⚡ 10x productivity: AI directly accesses ERP data
• 🎯 Target market: 7M+ Odoo users worldwide

Technical Impact

• 📊 15 MCP tools exposed and documented
• 🚀 Cloud-native with Modal integration
• 🔒 Production-ready with enterprise security

🔧 Technical Configuration

Environment Variables

# Odoo Configuration (required)
ODOO_URL="https://your-instance.odoo.com"
ODOO_DB="your-database"  
ODOO_USERNAME="your-email"
ODOO_PASSWORD="your-password"

# Modal Configuration (optional for ML)
MODAL_TOKEN="your-modal-token"

# MCP Configuration (auto)
GRADIO_MCP_SERVER="True"  # Activates MCP server

Detailed MCP Architecture

# Server exposes these MCP capabilities:
{
  "capabilities": {
    "tools": {
      "listChanged": true
    },
    "resources": {
      "subscribe": true  
    },
    "prompts": {
      "listChanged": true
    }
  }
}

🚀 Post-Hackathon Roadmap

V2.0 - Expansion

• Multi-instance Odoo support
• Marketing/Inventory MCP tools
• Integrated BI dashboard

V3.0 - Enterprise

• SSO/OAuth integration
• API rate limiting
• Advanced monitoring

V4.0 - Ecosystem

• Odoo MCP tools marketplace
• Third-party integrations (Salesforce, HubSpot)
• Autonomous AI agents

📞 Support & Contribution

• Live Demo: HuggingFace Space
• Documentation: Integrated step-by-step guides
• Issues: GitHub community support
• Contributions: PRs welcome!

---

🎯 MCP Hackathon 2025 - Track: MCP Server
Transforming Enterprise ERP with AI-Native Model Context Protocol

Made with ❤️ for the MCP community

📅 Hackathon Timeline

Here are the key dates for the Gradio Agents & MCP Hackathon:

• May 20 – 26, 2025: Pre-Hackathon announcements period
• June 2 – 10, 2025: Official hackathon window (sign-ups remain open)
• June 3, 2025 — 9 AM PST / 4 PM UTC: Live kickoff YouTube event
• June 4 – 5, 2025: Gradio Office Hours with MCP Support, MistralAI, LlamaIndex, Custom Components team, and Sambanova
• June 10, 2025 — 11:59 PM UTC: Final submission deadline
• June 11 – 16, 2025: Judging period
• June 17, 2025: Winners announced

👥 Key Players

Sponsors

• Modal Labs: $250 GPU/CPU credits to every participant (modal.com)
• Hugging Face: $25 API credits to every participant (huggingface.co)
• Nebius: $25 API credits to first 3,300 participants (nebius.com)
• Anthropic: $25 API credits to first 1,000 participants (anthropic.com)
• OpenAI: $25 API credits to first 1,000 participants (openai.com)
• Hyperbolic Labs: $15 API credits to first 1,000 participants (hyperbolic.xyz)
• MistralAI: $25 API credits to first 500 participants (mistral.ai)
• Sambanova.AI: $25 API credits to first 250 participants (sambanova.ai) (huggingface.co)

Panel of Judges

Judging will be conducted by representatives from sponsor partners and the Hugging Face community team, including Modal Labs, MistralAI, LlamaIndex, Sambanova.AI, and Hugging Face. To be properly judged, ensure the project is in the proper space on hugging face, not just in a personal space. Click join organization, then click new to create a space that will be judged.

Office Hours Hosts

• Abubakar Abid (MCP Support) — @abidlabs
• MistralAI Office Hours — Watch on YouTube
• LlamaIndex Office Hours — Watch on YouTube
• Custom Components Office Hours — Watch on YouTube
• Sambanova Office Hours — Watch on YouTube

Primary Organizers

• Yuvraj Sharma (Yuvi) (@yvrjsharma) — Machine Learning Engineer & Developer Advocate, Gradio Team at Hugging Face
• Abubakar Abid (@abidlabs) — Developer Advocate & MCP Support Lead at Hugging Face
• Gradio Team at Hugging Face — Core organizing team providing platform infrastructure, logistics, and community coordination

📚 Resources

• Hackathon Org & Registration: Agents-MCP-Hackathon
• Discord: discord.gg/agents-mcp-hackathon
• Slides from Kickoff: PDF
• Code of Conduct: Contributor Covenant
• Submission Guidelines: See "Submission Guidelines" on the hackathon page
• MCP Guide: How to Build an MCP Server
• Gradio Docs: https://www.gradio.app/docs
• LlamaIndex Docs: https://llamaindex.ai/docs
• Mistral Model Hub: https://huggingface.co/mistral-ai/mistral-small

🆓 Free Credits!

Modal Labs Compute Credits ($250 per participant) Monitor your GPU/CPU credit usage by logging into your Modal account and navigating to Dashboard → Billing: https://modal.com/dashboard

Hugging Face API Credits ($25 per participant) View your remaining credits and invoices on the Hugging Face billing dashboard: https://huggingface.co/settings/billing

Nebius AI Cloud Credits ($25 to first 3,300 participants) Check your Nebius "Grants and promocodes" balance and detailed billing reports at: https://nebius.com/services/billing

Anthropic Claude API Credits ($25 to first 1,000 participants) Track your Claude usage and remaining credits in the Anthropic Console under Settings → Billing: https://console.anthropic.com/settings/billing

OpenAI API Credits ($25 to first 1,000 participants) Monitor your API calls, token usage, and spend on the OpenAI Usage dashboard: https://platform.openai.com/account/usage

Hyperbolic Labs API Credits ($15 to first 1,000 participants) After logging in at the Hyperbolic AI Dashboard, go to Settings → Billing to view your credit balance and transaction history: https://app.hyperbolic.xyz

Mistral AI API Credits ($25 to first 500 participants) Sign in at the Mistral Console and navigate to Workspace → Billing to activate and monitor your credits: https://console.mistral.ai

SambaNova AI Cloud Credits ($25 to first 250 participants) Log in to SambaNova Cloud and check your Billing & Usage in the plans section: https://cloud.sambanova.ai/plans/billing

👤 About the Author

Graham Paasch is an AI realist passionate about the coming AI revolution.

• LinkedIn: https://www.linkedin.com/in/grahampaasch/
• YouTube: https://www.youtube.com/channel/UCg3oUjrSYcqsL9rGk1g_lPQ

Graham is currently looking for work. Inspired by Leopold Aschenbrenner's "AI Situational Awareness" (https://situational-awareness.ai/), he believes AI will become a multi-trillion-dollar industry over the next decade—what we're seeing now is the equivalent of ARPANET in the early days of the internet. He's committed to aligning his work with this vision to stay at the forefront of the AI revolution.