insurance-ai-mcp-server

chandan-akshronix/insurance-ai-mcp-server

3.1

If you are the rightful owner of insurance-ai-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

Main Control Point (MCP) backend service for the AI Automated Insurance Claim & Underwriting System.

Gk Mcp

Python 3.10+ FastMCP MCP

MCP Server built using Python

MCP Protocol Compliance: See for details.

Authentication

See for details.

MCP Server Components

Tools

Tools are functions that AI models can call to perform specific actions.

Prompts

Prompts are reusable templates that help AI models interact consistently with your server.

Resources

Resources provide AI models with access to external content.

Security Features

  • Implements origin validation to prevent DNS rebinding attacks
  • Uses Streamable HTTP transport in stateless mode for security
  • Only processes requests from trusted origins (localhost) in development
  • All API inputs are validated before processing

Project Layout

This project is organized using the src layout structure.

The following is a list of the src/insurance_mcp subdirectories and files:

FolderDescription
/configMCP Server configuration files for MCP Server deployment in local and cloud environments.
/controllersThe file mcp_controller.py exposes the MCP Tools provided by this MCP Server and invokes the business logic services.
/servicesBusiness logic services.
/repositoriesData access/repository layer.
/middlewareFilters and Handlers classes to support MCP Message Handling best practices
/utilsUtility classes and exceptions used across MCP tools during request execution.
/modelsDefines the data models.
server.pyHTTP server with MCP streamable capabilities

Run the MCP Server

Prerequisites

  • Python 3.10+<3.13
  • fastmcp
  • pydantic 2.0.0+
  • uvicorn 0.15.0+
  • uv

Step 1: Install uv Package Manager

  1. Install the package using uv: A fast Python Package Manager (You don't need to be connected to a VPN to download it)

Step 2: Clone Repository

  1. Clone the repository:
git clone repo_link
cd repo_name

Step 3: Configuration

  • PORT: Server port (default: 8080)

Step 4: Set Up Python Environment

  1. Install the dependencies with [uv]
uv sync
source .venv/bin/activate

Step 5: Run the Unit Tests

Run the test suite:

uv pip install "insurance-mcp[tests]"
uv run pytest

Step 6: Start the MCP Server

  1. Configure authentication using the steps above
  2. Start the MCP Server:
insurance-mcp

Congratulations! Your MCP server is now running at https://localhost:8080/mcp/

Step 7: Test the MCP Server

Initial setup includes the following MCP Server Tools:

  • get_by_id: Allows LLMs to get an gkmcp by ID
  • mcp_list: Enables LLMs to get all gkmcps

📝 Detailed Testing: See

Deployment

Health Check Validation
https://deployed_link.com/health
```

Monitoring & Observability

Golden Signals Dashboard

The server exposes Prometheus metrics for Monitoring and Observability.

For metrics and Golden Signals configurations check this project's

Distributed Tracing

This MCP server supports the OpenTelemetry distributed tracing standard.

Tracestore Onboarding

Development

Contributions are welcome! Please follow the guidelines below:

  • Fork the repository.
  • Create a feature branch.
  • Commit your changes.
  • Submit a pull request.

Support

For issues or questions:

insurance-ai-mcp-server

Main Control Point (MCP) backend service for the AI Automated Insurance Claim & Underwriting System. Handles claim orchestration, Kafka-based messaging, and integration with AI agents, databases, and observability tools.