AI Customer Support Bot - MCP Server

A Model Context Protocol (MCP) server that provides AI-powered customer support using Cursor AI and Glama.ai integration.

Features

Real-time context fetching from Glama.ai
AI-powered response generation with Cursor AI
Batch processing support
Priority queuing
Rate limiting
User interaction tracking
Health monitoring
MCP protocol compliance

Prerequisites

Python 3.8+
PostgreSQL database
Glama.ai API key
Cursor AI API key

Installation

Clone the repository:

git clone <repository-url>
cd <repository-name>

Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

Install dependencies:

pip install -r requirements.txt

Create a .env file based on .env.example:

cp .env.example .env

Configure your .env file with your credentials:

# API Keys
GLAMA_API_KEY=your_glama_api_key_here
CURSOR_API_KEY=your_cursor_api_key_here

# Database
DATABASE_URL=postgresql://user:password@localhost/customer_support_bot

# API URLs
GLAMA_API_URL=https://api.glama.ai/v1

# Security
SECRET_KEY=your_secret_key_here

# MCP Server Configuration
SERVER_NAME="AI Customer Support Bot"
SERVER_VERSION="1.0.0"
API_PREFIX="/mcp"
MAX_CONTEXT_RESULTS=5

# Rate Limiting
RATE_LIMIT_REQUESTS=100
RATE_LIMIT_PERIOD=60

# Logging
LOG_LEVEL=INFO

Set up the database:

# Create the database
createdb customer_support_bot

# Run migrations (if using Alembic)
alembic upgrade head

Running the Server

Start the server:

python app.py

The server will be available at http://localhost:8000

API Endpoints

1. Root Endpoint

GET /

Returns basic server information.

2. MCP Version

GET /mcp/version

Returns supported MCP protocol versions.

3. Capabilities

GET /mcp/capabilities

Returns server capabilities and supported features.

4. Process Request

POST /mcp/process

Process a single query with context.

Example request:

curl -X POST http://localhost:8000/mcp/process \
  -H "Content-Type: application/json" \
  -H "X-MCP-Auth: your-auth-token" \
  -H "X-MCP-Version: 1.0" \
  -d '{
    "query": "How do I reset my password?",
    "priority": "high",
    "mcp_version": "1.0"
  }'

5. Batch Processing

POST /mcp/batch

Process multiple queries in a single request.

Example request:

curl -X POST http://localhost:8000/mcp/batch \
  -H "Content-Type: application/json" \
  -H "X-MCP-Auth: your-auth-token" \
  -H "X-MCP-Version: 1.0" \
  -d '{
    "queries": [
      "How do I reset my password?",
      "What are your business hours?",
      "How do I contact support?"
    ],
    "mcp_version": "1.0"
  }'

6. Health Check

GET /mcp/health

Check server health and service status.

Rate Limiting

The server implements rate limiting with the following defaults:

100 requests per 60 seconds
Rate limit information is included in the health check endpoint
Rate limit exceeded responses include reset time

Error Handling

The server returns structured error responses in the following format:

{
  "code": "ERROR_CODE",
  "message": "Error description",
  "details": {
    "timestamp": "2024-02-14T12:00:00Z",
    "additional_info": "value"
  }
}

Common error codes:

RATE_LIMIT_EXCEEDED: Rate limit exceeded
UNSUPPORTED_MCP_VERSION: Unsupported MCP version
PROCESSING_ERROR: Error processing request
CONTEXT_FETCH_ERROR: Error fetching context from Glama.ai
BATCH_PROCESSING_ERROR: Error processing batch request

Development

Project Structure

.
├── app.py              # Main application file
├── database.py         # Database configuration
├── middleware.py       # Middleware (rate limiting, validation)
├── models.py          # Database models
├── mcp_config.py      # MCP-specific configuration
├── requirements.txt   # Python dependencies
└── .env              # Environment variables

Adding New Features

Update mcp_config.py with new configuration options
Add new models in models.py if needed
Create new endpoints in app.py
Update capabilities endpoint to reflect new features

Security

All MCP endpoints require authentication via X-MCP-Auth header
Rate limiting is implemented to prevent abuse
Database credentials should be kept secure
API keys should never be committed to version control

Monitoring

The server provides health check endpoints for monitoring:

Service status
Rate limit usage
Connected services
Processing times

Contributing

Fork the repository
Create a feature branch
Commit your changes
Push to the branch
Create a Pull Request

Flowchart

Verification Badge

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

For support, please create an issue in the repository or contact the development team.

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

A Model Context Protocol (MCP) server that provides AI-powered customer support using Cursor AI and Glama.ai integration.

Related MCP Servers

Cursor MCP Installer
matthewdcage
-
security
A
license
-
quality
A Model Context Protocol (MCP) server for Cursor IDE that simplifies the installation and configuration of other MCP servers.
Last updated -
882
23
JavaScript
MIT License
DroidMind
hyperb1iss
A
security
A
license
A
quality
A Model Context Protocol (MCP) server that enables AI assistants to control and interact with Android devices, allowing for device management, app debugging, system analysis, and UI automation through natural language commands.
Last updated -
29
143
Python
Apache 2.0
AI Customer Support Bot - MCP Server
ChiragPatankar
-
security
A
license
-
quality
A Model Context Protocol (MCP) server that provides AI-powered customer support using Cursor AI and Glama.ai integration.
Last updated -
1
Python
MIT License
1MCP Server
1mcp-app
-
security
A
license
-
quality
A unified Model Context Protocol server that aggregates multiple MCP servers into one, allowing AI assistants like Claude Desktop, Cursor, and Cherry Studio to connect to a single server instead of managing multiple instances.
Last updated -
59
21
TypeScript
Apache 2.0

View all related MCP servers

AI Customer Support Bot - MCP Server