--- title: CX AI Agent - B2B Sales Intelligence emoji: π€ colorFrom: blue colorTo: purple sdk: gradio sdk_version: 5.33.0 app_file: app.py pinned: false license: mit short_description: AI-powered B2B sales automation with MCP tools tags: - mcp-in-action-track-enterprise - mcp - autonomous-agent - b2b-sales - prospect-discovery - email-automation - gradio - huggingface - qwen - sales-intelligence --- # π€ CX AI Agent - B2B Sales Intelligence Platform [](https://github.com) [](https://huggingface.co) [](https://gradio.app) > **π MCP in Action Track - Enterprise Applications** > > Tag: `mcp-in-action-track-enterprise` ## πΉ Overview An AI-powered B2B sales automation platform that helps sales teams discover prospects, find decision-makers, and draft personalized outreach emailsβall powered by autonomous AI agents using the **Model Context Protocol (MCP)**. ## π― Key Features | Feature | Description | |---------|-------------| | **π AI Discovery** | Automatically find and research prospect companies matching your ideal customer profile | | **π₯ Contact Finder** | Locate decision-makers (CEOs, VPs, Founders) with verified email addresses | | **βοΈ Email Drafting** | Generate personalized cold outreach emails based on company research | | **π¬ AI Chat** | Interactive assistant for pipeline management and real-time research | | **π€ Prospect Chat** | Demo of prospect-facing AI with handoff & escalation capabilities | | **π Dashboard** | Real-time pipeline metrics and progress tracking | ## π Quick Start 1. **Setup**: Enter your HuggingFace token and company name 2. **Discover**: Let AI find prospects matching your profile 3. **Review**: Check discovered companies and contacts 4. **Engage**: Use AI-drafted emails for outreach ## ποΈ Architecture ``` βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ β CX AI Agent β βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ€ β βββββββββββββββ βββββββββββββββ βββββββββββββββ β β β Gradio β β Autonomousβ β MCP β β β β UI ββββ Agent ββββ Servers β β β βββββββββββββββ βββββββββββββββ βββββββββββββββ β β β β β β β βΌ βΌ βΌ β β βββββββββββββββββββββββββββββββββββββββββββββββββββ β β β MCP Tool Definitions β β β β β’ Search (Web, News) β β β β β’ Store (Prospects, Contacts, Facts) β β β β β’ Email (Send, Thread Management) β β β β β’ Calendar (Meeting Slots, Invites) β β β βββββββββββββββββββββββββββββββββββββββββββββββββββ β ββββββββββββββββββββββββββββββββββββββββββββββ_βββββββββββββββββ ``` ## π§ MCP Tools Available ### Search MCP Server - `search_web` - Search the web for company information - `search_news` - Find recent news about companies ### Store MCP Server - `save_prospect` / `get_prospect` / `list_prospects` - Manage prospects - `save_company` / `get_company` - Store company data - `save_contact` / `list_contacts_by_domain` - Manage contacts - `discover_prospects_with_contacts` - Full discovery pipeline - `find_verified_contacts` - Find decision-makers ### Email MCP Server - `send_email` - Send outreach emails - `get_email_thread` - Retrieve conversation history ### Calendar MCP Server - `suggest_meeting_slots` - Generate available times - `generate_calendar_invite` - Create .ics files ## π Prospect Chat Demo The **Prospect Chat Demo** showcases how prospects can interact with your company's AI: - **Lead Qualification**: AI asks qualifying questions to understand prospect needs - **Handoff Packets**: Generate comprehensive summaries for human sales reps - **Escalation Flows**: Automatically escalate complex inquiries to humans - **Meeting Scheduling**: Integrate with calendar for instant booking ## π Technology Stack | Component | Technology | |-----------|------------| | **Frontend** | Gradio 5.x | | **AI Model** | Qwen2.5-72B / Qwen3-32B via HuggingFace | | **Protocol** | Model Context Protocol (MCP) | | **Search** | Serper API | | **Language** | Python 3.8+ | ## π Environment Variables Set these in your Space Secrets: ``` HF_TOKEN=your_huggingface_token_here SERPER_API_KEY=your_serper_api_key_here # Optional ``` ## π Project Structure ``` cx-ai-agent/ βββ app.py # Main Gradio application βββ requirements.txt # Python dependencies βββ README.md # This file βββ app/ β βββ schema.py # Pydantic data models βββ mcp/ βββ agents/ # Autonomous AI agents βββ servers/ # MCP server implementations βββ tools/ βββ definitions.py # MCP tool definitions ``` ## π License This project is open source and available under the MIT License. ## π Acknowledgments - **Anthropic** - Model Context Protocol specification - **HuggingFace** - AI model hosting and inference - **Gradio** - UI framework - **Serper** - Web search API --- ## π¨βπ» Developer **Syed Muzakkir Hussain** [](https://huggingface.co/muzakkirhussain011) ---