Qmed-AskCPG
Officialby qmed-asia
README.md
# Qmed-AskCPG
**Qmed-AskCPG** is a Python package that allows clinicians and developers to query Malaysian Clinical Practice Guidelines (CPGs) using natural language. It leverages the MCP (Medical Content Pipeline) server to return structured responses based on official CPG references.
π¦ PyPI: [https://pypi.org/project/mcp-askcpg/](https://pypi.org/project/mcp-askcpg/)
---
## π§ Installation
Install the package via pip:
```bash
pip install mcp-askcpg
```
---
## βοΈ Manual Configuration (Example)
If you are using a `uvx`-based setup or a JSON-based task runner, you can manually configure the environment as follows:
```json
"clinical_practice_guide": {
"command": "uvx",
"args": ["mcp-askcpg"],
"env": {
"ASKCPG_API_KEY": "<PLEASE_ASK_ME>",
"ASKCPG_BACKEND": "<PLEASE_ASK_ME>"
}
}
```
> **Note:** Please contact the maintainer to obtain your `ASKCPG_API_KEY` and `ASKCPG_BACKEND` values.
---
## π¬ Example Query
Once the server is running, you can ask a question like:
```text
Please tell me the procedure of stroke management in CPG?
```
The system will return a structured response based on Malaysiaβs official clinical guidelines.
---
## π References
This project is built on the MCP structured reference system:
π [https://github.com/adhikasp/mcp-twikit](https://github.com/adhikasp/mcp-twikit)
---
## π How We Published to PyPI
We followed this excellent guide for publishing directly from GitHub:
π [Publishing a Python Package to PyPI in 2024](https://medium.com/@blackary/publishing-a-python-package-from-github-to-pypi-in-2024-a6fb8635d45d)
---
## π© Contact
For access credentials or collaboration inquiries, please contact the Qmed Asia team.
---
## π₯ About Qmed Asia
Qmed Asia is a health technology company focused on building digital tools for clinicians and pharmacists. Our goal is to make evidence-based medicine more accessible and actionable through intelligent clinical infrastructure.
---
## π·οΈ Tags
`clinical-guidelines` β’ `malaysia` β’ `medical-ai` β’ `nlp` β’ `mcp` β’ `python` β’ `healthtech`
TDQS
B3/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no risk of confusion between tools. The agent can uniquely identify the tool's purpose.
Naming Consistency5/5
The single tool name 'get_cpg_context' follows a clear verb_noun pattern, consistent with common MCP naming conventions.
Tool Count3/5
A single tool for querying clinical guidelines is minimalist but functional. The server's scope is narrow, yet a few more tools (e.g., list_guidelines) could improve coverage.
Completeness3/5
The server provides only retrieval of context from medical books. Missing operations like listing available guidelines or retrieving full sections, but the tool may suffice for simple Q&A tasks.
Maintenance
ActivityInactive
ResponsivenessNo issues