Hong Kong Health Data MCP Server
# Hong Kong Health Data MCP Server
[](https://github.com/hkopenai/hk-health-mcp-server)
[](https://opensource.org/licenses/MIT)
This is an MCP server that provides access to health related data in Hong Kong through a FastMCP interface.
## Features
1. Get current Accident and Emergency Department waiting times by hospital in Hong Kong
2. Get current waiting times for new case bookings for specialist outpatient services by specialty and cluster in Hong Kong
3. Get average number of general outpatient clinic quotas for the preceding 4 weeks across 18 districts in Hong Kong
## Examples
* As a news reporter, you are interested in knowing the current waiting times at hospitals in Hong Kong. Please remind the audience not to abuse the service. Report in Chinese.
* As a healthcare professional, you need to check the current waiting times for specialist outpatient services in different clusters to advise patients on the best options for timely care.
## Data Source
* Hong Kong Hospital Authority
## Setup
1. Clone this repository
2. Install Python dependencies:
```bash
pip install -r requirements.txt
```
3. Run the server:
```bash
python server.py
```
### Running Options
- Default stdio mode: `python server.py`
- SSE mode (port 8000): `python server.py --sse`
## Cline Integration
To connect this MCP server to Cline using stdio:
1. Add this configuration to your Cline MCP settings (cline_mcp_settings.json):
```json
{
"hk-health": {
"disabled": false,
"timeout": 3,
"type": "stdio",
"command": "uvx",
"args": [
"hkopenai.hk-health-mcp-server"
]
}
}
```
## Testing
Tests are available in the `tests/` directory. Run with:
```bash
pytest
```
TDQS
Scored across 3 tools
Each tool targets a distinct health service resource: AED waiting times, specialist outpatient waiting times, and general outpatient clinic quotas. There is no overlap in purpose or data returned.
The first two tools follow a clear 'get_<service>_waiting_times' pattern, but the third tool deviates with 'get_pas_gopc_avg_quota' using a different structure. Still, all use the 'get_' prefix and are readable.
With only three tools, the server is tightly focused on Hong Kong public health waiting times and quotas. Each tool addresses a distinct data need, making the count well-scoped for its niche purpose.
The server covers the main public waiting time categories: A&E, specialist outpatient, and general outpatient clinics. Minor gaps exist such as private healthcare or specific procedure wait times, but the core domain is reasonably complete.