Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Qmed-AskCPG What is the CPG recommendation for diabetes management?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
📦 PyPI: https://pypi.org/project/mcp-askcpg/
Install the package via pip:
pip install mcp-askcpgRelated MCP server: cdisc-mcp
If you are using a uvx-based setup or a JSON-based task runner, you can manually configure the environment as follows:
"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_KEYandASKCPG_BACKENDvalues.
Once the server is running, you can ask a question like:
Please tell me the procedure of stroke management in CPG?The system will return a structured response based on Malaysia’s official clinical guidelines.
This project is built on the MCP structured reference system:
🔗 https://github.com/adhikasp/mcp-twikit
We followed this excellent guide for publishing directly from GitHub:
📝 Publishing a Python Package to PyPI in 2024
For access credentials or collaboration inquiries, please contact the Qmed Asia team.
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.
clinical-guidelines • malaysia • medical-ai • nlp • mcp • python • healthtech
Get context from medical clinical practice guideline books based on user query.
Args:
input_queries: user query to get the context from the medical books.
| Name | Required | Description | Default |
|---|---|---|---|
| input_queries | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits. It fails to mention what 'context' means (e.g., snippets, full paragraphs), how results are ordered or filtered, or any authentication or rate limit requirements. The tool appears to be a retrieval function but offers no details on behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short but includes an 'Args' section, providing some structure. However, the main sentence is slightly redundant ('based on user query' and 'user query'). It could be tightened without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and low schema coverage, the description should be more complete. It does not specify the return format, error cases, or what constitutes a valid query. For a retrieval tool, this is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage; the input_queries parameter has only a title. The description adds 'user query to get the context from the medical books,' which merely restates the parameter's role. No format constraints, length limits, or query structure hints are provided.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: getting context from medical clinical practice guideline books based on a user query. The verb 'Get' and resource 'context' are specific, and the domain is clear. However, no sibling tools are provided for comparison, so the score is not a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description lacks any guidance on when to use this tool vs alternatives, prerequisites, or limitations. It simply states the action without contextual boundaries. No 'when not to use' or alternative tool suggestions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no risk of confusion between tools. The agent can uniquely identify the tool's purpose.
The single tool name 'get_cpg_context' follows a clear verb_noun pattern, consistent with common MCP naming conventions.
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.
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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
Medical RAG: semantic search for clinical guidelines, drug interactions, diagnoses & EHR data.
GRADE-rated clinical evidence on cannabis as medicine (DE/EN). Search and cite studies.
The adaptive health-messaging engine for apps and agents. Federally-sourced. Not medical advice.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/qmed-asia/mcp-askcpg'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
