Absher Voice Assistant MCP Server

Absher Voice Assistant MCP Server

Enables interaction with Saudi government services through the Absher platform, supporting identity verification, user profile management, and service discovery. It allows users to perform tasks like renewing passports, querying traffic fines, and booking appointments using natural language.

Category
Visit Server

README

Absher Voice Assistant MCP Server

Standalone MCP (Model Context Protocol) server for Saudi government services (Absher platform).

Overview

This MCP server provides 8 tools for handling authentication, user data, and government services:

Authentication & Identity Tools (3)

  1. verify_national_id - Check if a national ID exists in the system
  2. get_security_questions - Fetch security questions for user verification
  3. verify_security_answers - Verify user's answers to security questions

User Data Tool (1)

  1. get_user_data - Load complete user profile information

Service Discovery Tool (1)

  1. get_service_requirements - Get required fields for a specific service

Service Execution Tools (3)

  1. renew_passport - Submit passport renewal request
  2. get_traffic_fines - Query traffic violations
  3. book_appointment - Schedule government office appointment

Installation

# Install dependencies
pip install -r requirements.txt

Running the Server

Standalone Mode (for testing)

python absher_server.py

With MCP Client (recommended)

Use with any MCP-compatible client (Claude Desktop, custom clients, etc.)

Example configuration for Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "absher": {
      "command": "python",
      "args": ["/path/to/mcp-servers/absher_server.py"]
    }
  }
}

Mock Data

The server includes 3 test users:

User 1

  • National ID: 1234567890
  • Name: أحمد محمد
  • Passport: A12345678
  • Traffic Fines: 2 unpaid fines (650 SAR total)
  • Security Question: ما هو اسم مدينة ميلادك? → الرياض

User 2

  • National ID: 0987654321
  • Name: فاطمة أحمد
  • Passport: B98765432
  • Traffic Fines: 1 paid fine
  • Security Question: ما هو اسم مدينة ميلادك? → جدة

User 3

  • National ID: 1122334455
  • Name: خالد عبدالله
  • Passport: C11223344
  • Traffic Fines: None
  • Security Question: ما هو اسم مدينة ميلادك? → الدمام

Tool Usage Examples

1. Verify National ID

verify_national_id(national_id="1234567890")
# Returns: {"exists": true, "message": "تم العثور على رقم الهوية الوطنية في النظام"}

2. Get Security Questions

get_security_questions(national_id="1234567890")
# Returns: {"success": true, "questions": [{"question_id": "q1", "question": "ما هو اسم مدينة ميلادك؟"}]}

3. Verify Security Answers

verify_security_answers(
    national_id="1234567890",
    answers=[{"question_id": "q1", "answer": "الرياض"}]
)
# Returns: {"verified": true, "message": "تم التحقق من هويتك بنجاح"}

4. Get User Data

get_user_data(national_id="1234567890")
# Returns: Complete user profile with name, phone, passport info, etc.

5. Get Service Requirements

get_service_requirements(service_name="passport_renewal")
# Returns: List of required fields with sources (user_data vs user_input)

6. Renew Passport

renew_passport(
    national_id="1234567890",
    renewal_reason="انتهاء الصلاحية",
    delivery_method="استلام من المكتب"
)
# Returns: {"success": true, "request_id": "PR20241208123456", "message": "..."}

7. Get Traffic Fines

get_traffic_fines(national_id="1234567890")
# Returns: List of fines with summary (total, unpaid, amount)

8. Book Appointment

book_appointment(
    national_id="1234567890",
    service_type="الجوازات",
    location="الرياض",
    preferred_date="2024-12-15"
)
# Returns: {"success": true, "appointment_id": "APT20241208123456", "details": {...}}

Authentication Flow (as per new_flow.txt)

  1. Identity Check: Call verify_national_id with user's national ID
  2. Security Questions: Call get_security_questions to fetch questions
  3. Security Verification: Ask user questions one-by-one, then call verify_security_answers
  4. Load User Data: Call get_user_data after successful verification
  5. Service Selection: User chooses a service
  6. Requirements Check: Call get_service_requirements to see what's needed
  7. Data Collection: Ask for missing information one question at a time
  8. Confirmation: Show summary and ask for confirmation
  9. Execution: Call service tool (renew_passport, get_traffic_fines, book_appointment)
  10. Confirmation: Return success message to user

Service Requirements

Passport Renewal

Required from user_data: national_id, first_name, last_name, phone, passport_number Required from user_input: renewal_reason, delivery_method

renewal_reason options:

  • انتهاء الصلاحية
  • تلف
  • ضياع
  • امتلاء الصفحات

delivery_method options:

  • استلام من المكتب
  • توصيل بالبريد

Traffic Fines

Required from user_data: national_id

Book Appointment

Required from user_data: national_id Required from user_input: service_type, location, preferred_date

service_type options:

  • الجوازات
  • الأحوال المدنية
  • المرور

location options:

  • الرياض
  • جدة
  • الدمام

Files

  • absher_server.py - Main MCP server with all 8 tools
  • mock_data.py - Mock users, fines, appointments, and service requirements
  • requirements.txt - Python dependencies
  • README.md - This file

Integration with AI Clients

This MCP server is designed to work with any MCP-compatible AI client:

  • Claude Desktop: Add to config file
  • OpenAI Realtime API: Use with custom MCP client bridge
  • Ollama: Use with mcp_client.py bridge
  • Custom Clients: Any client that supports MCP protocol

The server is fully independent and stateless - all data is in mock_data.py.

Notes

  • All responses are in Arabic with English function names
  • Server uses stdio transport (standard MCP approach)
  • All tools return JSON strings for easy parsing
  • Mock data can be easily extended or replaced with real database

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Absher Voice Assistant MCP Server