Respona Dashboard MCP Server

An MCP (Model Context Protocol) server that provides tools to interact with the Respona Dashboard backend API. This server allows users to query ticket data, analytics, and AI flags through natural language interactions.

Features

This MCP server implements 13 tools corresponding to the Respona Dashboard API endpoints:

Ticket Management Tools

• get_tickets - Retrieve tickets with filtering and pagination

• get_ticket_stats - Get ticket statistics and metrics

• get_ticket_by_id - Retrieve a specific ticket by ID

• get_ticket_ai_analysis - Get AI analysis for a specific ticket

Analytics Tools

• get_ai_flags_distribution - Get AI flags distribution for analytics

• get_similar_incidents - Get count of similar incidents

• get_source_channels_distribution - Get distribution of ticket source channels

• get_priority_distribution - Get distribution of ticket priorities

• get_status_distribution - Get distribution of ticket statuses

• get_dashboard_analytics - Get comprehensive analytics for dashboard

AI Flags Tools

• get_analysis_flags - Get all flags for a specific AI analysis

• get_analysis_flag_stats - Get flag statistics for an AI analysis

• get_all_flags - Get all flags with pagination (admin view)

Installation

1. Clone the repository:

   git clone <repository-url>
   cd respona_mcp_server

2. Install dependencies:

   pip install -e .

   Or using uv (recommended):

   uv pip install -e .

3. Set up configuration:

   cp .env.example .env
   # Edit .env with your configuration

Configuration

The server can be configured through environment variables or a .env file:

API Configuration

• RESPONA_API_BASE_URL: Base URL for the Respona Dashboard API (default: http://10.250.201.107:3001)

• RESPONA_API_KEY: API key for authentication (optional)

Request Configuration

• RESPONA_REQUEST_TIMEOUT: Request timeout in seconds (default: 30)

• RESPONA_MAX_RETRIES: Maximum number of request retries (default: 3)

Pagination Configuration

• RESPONA_DEFAULT_PAGE_SIZE: Default number of items per page (default: 20)

• RESPONA_MAX_PAGE_SIZE: Maximum allowed page size (default: 100)

Usage

Running the Server

# Run directly
python -m respona_mcp_server

# Or using the installed script
respona-mcp-server

MCP Client Configuration

Add this server to your MCP client configuration. For example, in Claude Desktop, add to your claude_desktop_config.json:

{
  "mcpServers": {
    "respona-dashboard": {
      "command": "python",
      "args": ["-m", "respona_mcp_server"],
      "env": {
        "RESPONA_API_BASE_URL": "http://10.250.201.107:3001"
      }
    }
  }
}

Or if you have the package installed globally:

{
  "mcpServers": {
    "respona-dashboard": {
      "command": "respona-mcp-server",
      "env": {
        "RESPONA_API_BASE_URL": "http://10.250.201.107:3001"
      }
    }
  }
}

Tool Usage Examples

Get All Tickets

Get me all tickets with high priority from the last week

Get Ticket Statistics

Show me the current ticket statistics

Get Specific Ticket

Show me details for ticket ID 12345

Get Analytics

What's the distribution of ticket priorities?

Filter Tickets

Show me all tickets assigned to John Doe with status "open"

Get AI Analysis

Get the AI analysis for ticket 67890

API Endpoints Mapping

Error Handling

The server includes comprehensive error handling:

• Network Errors: Automatic retries with exponential backoff

• API Errors: Proper HTTP status code handling

• Parameter Validation: Input validation with helpful error messages

• Connection Issues: Graceful handling of API server downtime

Development

Running Tests

pytest

Code Formatting

ruff format .
ruff check .

Type Checking

mypy respona_mcp_server/

Troubleshooting

Common Issues

1. Connection Refused

   • Check if the Respona API server is running

   • Verify the RESPONA_API_BASE_URL configuration

   • Check network connectivity

2. Authentication Errors

   • Verify API key configuration if required

   • Check if the API key has proper permissions

3. Timeout Errors

   • Increase RESPONA_REQUEST_TIMEOUT

   • Check network latency to the API server

Logging

The server uses Python's standard logging. Set the log level:

export PYTHONPATH=.
python -m respona_mcp_server --log-level DEBUG

Contributing

1. Fork the repository

2. Create a feature branch

3. Make your changes

4. Add tests

5. Run the test suite

6. Submit a pull request

License

MIT License - see LICENSE file for details.