AI Customer Support Bot - MCP Server

by ChiragPatankar

4 stars
184 downloads
Not rated
GitHub

Description

# πŸ€– AI Customer Support Bot - MCP Server <div align="center"> ![Python](https://img.shields.io/badge/python-v3.8+-blue.svg) ![FastAPI](https://img.shields.io/badge/FastAPI-005571?style=flat&logo=fastapi)…

About

# πŸ€– AI Customer Support Bot - MCP Server <div align="center"> ![Python](https://img.shields.io/badge/python-v3.8+-blue.svg) ![FastAPI](https://img.shields.io/badge/FastAPI-005571?style=flat&logo=fastapi) ![PostgreSQL](https://img.shields.io/badge/PostgreSQL-316192?style=flat&logo=postgresql&logoColor=white)…

Details

Author
ChiragPatankar
GitHub stars
4
Downloads
184
Categories
Search

- Full MCP protocol implementation
- Production-ready with auth, rate limiting, and monitoring
- High performance with FastAPI async support
- AI-agnostic – integrate any provider (OpenAI, Anthropic, etc.)
- Batch processing for multiple queries
- Secure by default: token auth, input validation, audit logging

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name AI Customer Support Bot - MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Clone the repository, create a virtual environment with Python 3.8+, install dependencies from requirements.txt, copy and edit .env.example to configure your database and AI service credentials, then run python app.py. The server starts at http://localhost:8000.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "ai customer support bot - mcp server": {
            "AI-Customer-Support-Bot--MCP-Server": {
                "command": "python",
                "args": [
                    "-m",
                    "venv",
                    "venv"
                ]
            }
        }
    }
}

McpServers

{
    "AI-Customer-Support-Bot--MCP-Server": {
        "command": "python",
        "args": [
            "-m",
            "venv",
            "venv"
        ]
    }
}

πŸ€– AI Customer Support Bot - MCP Server

<div align="center"> Python FastAPI PostgreSQL MCP License A modern, extensible MCP server framework for building AI-powered customer support systems Features β€’ Quick Start β€’ API Reference β€’ Architecture β€’ Contributing </div> ---

🌟 Overview

A Model Context Protocol (MCP) compliant server framework built with modern Python. Designed for developers who want to create intelligent customer support systems without vendor lock-in. Clean architecture, battle-tested patterns, and ready for any AI provider. ``mermaid graph TB Client[HTTP Client] --> API[API Server] API --> MW[Middleware Layer] MW --> SVC[Service Layer] SVC --> CTX[Context Manager] SVC --> AI[AI Integration] SVC --> DAL[Data Access Layer] DAL --> DB[(PostgreSQL)] `

✨ Features

<table> <tr> <td> πŸ—οΈ Clean Architecture Layered design with clear separation of concerns πŸ“‘ MCP Compliant Full Model Context Protocol implementation </td> <td> πŸ”’ Production Ready Auth, rate limiting, monitoring included πŸš€ High Performance Built on FastAPI with async support </td> </tr> <tr> <td> πŸ”Œ AI Agnostic Integrate any AI provider easily πŸ“Š Health Monitoring Comprehensive metrics and diagnostics </td> <td> πŸ›‘οΈ Secure by Default Token auth and input validation πŸ“¦ Batch Processing Handle multiple queries efficiently </td> </tr> </table>

πŸš€ Quick Start

Prerequisites

- Python 3.8+ - PostgreSQL - Your favorite AI service (OpenAI, Anthropic, etc.)

Installation

``bash
No reviews yet β€” be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.