Nccn Guidelines MCP
N

Nccn Guidelines MCP

A server based on the Model Context Protocol (MCP) that provides access to clinical guidelines from the National Comprehensive Cancer Network (NCCN). This system ensures the accuracy and reliability of medical guidance by directly reading the PDF content of the guidelines instead of using RAG technology.
2.5 points
3.7K

What is the NCCN Guidelines MCP Server?

This is a server based on the Model Context Protocol (MCP) for accessing and providing clinical guidelines from the National Comprehensive Cancer Network (NCCN). It can automatically acquire, download, and extract the content of NCCN guidelines, providing users with accurate medical advice.

How to use the NCCN Guidelines MCP Server?

By configuring MCP - supported client tools (such as Cursor, Claude Desktop, etc.) and connecting to this server, users can query NCCN guidelines and obtain relevant medical information.

Applicable Scenarios

Suitable for medical professionals, researchers, or patients who need to quickly access the latest NCCN clinical guidelines, helping them make more scientific medical decisions.

Main Features

Guideline Index Management
Automatically acquire and maintain the latest index of NCCN guidelines to ensure that the information accessed by users is up - to - date.
PDF Download
Support downloading guideline PDF files from the NCCN website and provide authentication support.
Content Extraction
Extract the content of specific pages from a PDF while keeping the original format unchanged.
Intelligent Caching
Cache index data for 7 days to reduce server load and improve response speed.
Advantages
Provide accurate NCCN guideline content to ensure the reliability of medical advice.
Read guideline content directly without relying on RAG (Retrieval - Augmented Generation), avoiding information distortion.
Support intelligent caching to enhance the user experience.
Easy to integrate into various MCP - compatible client tools.
Limitations
The index needs to be initialized when starting the server for the first time, which may result in a long waiting time.
Downloading and parsing PDFs may take some time, affecting the response speed.
An NCCN account is required for login, increasing the usage threshold.
Currently, only specific MCP client tools (such as Cursor, Claude Desktop, etc.) are supported.

How to Use

Clone the Repository
Clone the project code to your local computer.
Install Dependencies
Use uv to install all necessary Python dependencies.
Configure the Client
Configure the server parameters in the MCP - supported client, including NCCN account information.
Start the Server
Run the server to start providing NCCN guideline services.

Usage Examples

Immunotherapy Options Query
A user asks about the available first - line immunotherapy options for ES - SCLC (Extensive - Stage Small - Cell Lung Cancer).
Chemotherapy Options Query
A user asks about the initial chemotherapy for triple - negative breast cancer.
Immunotherapy Selection Query
A user asks about the immunotherapy options for neuroendocrine tumors.

Frequently Asked Questions

Do I need an NCCN account to use this server?
Why does it take so long to start the server for the first time?
Which client tools can I use to connect to this server?
What should I do if I encounter a download failure or parsing error?

Related Resources

NCCN Official Website
View the latest NCCN clinical guidelines and relevant medical information.
MCP Protocol Specification
Understand the detailed technical specifications of the Model Context Protocol (MCP).
GitHub Repository
View the project source code and the latest version updates.
PyPDF Documentation
Learn how to use the PyPDF library to process PDF files.
HTTPX Documentation
Understand the usage of the HTTPX library for asynchronous HTTP requests.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "nccn-guidelines": {
      "command": "uv",
      "args": ["--directory", "<abslute_direction_of_NCCN_guidelines_MCP>", "run", "server.py"],
      "env": {
        "NCCN_USERNAME": "<your_nccn_username>",
        "NCCN_PASSWORD": "<your_nccn_password>"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

K
Klavis
Klavis AI is an open-source project that provides a simple and easy-to-use MCP (Model Context Protocol) service on Slack, Discord, and Web platforms. It includes various functions such as report generation, YouTube tools, and document conversion, supporting non-technical users and developers to use AI workflows.
TypeScript
9.7K
5 points
S
Scrapling
Scrapling is an adaptive web scraping library that can automatically learn website changes and re - locate elements. It supports multiple scraping methods and AI integration, providing high - performance parsing and a developer - friendly experience.
Python
8.1K
5 points
A
Apple Health MCP
An MCP server for querying Apple Health data via SQL, implemented based on DuckDB for efficient analysis, supporting natural language queries and automatic report generation.
TypeScript
10.7K
4.5 points
M
MCP Server Airbnb
Certified
MCP service for Airbnb listing search and details query
TypeScript
13.6K
4 points
F
Firecrawl MCP Server
The Firecrawl MCP Server is a Model Context Protocol server integrating Firecrawl's web - scraping capabilities, providing rich web - scraping, searching, and content - extraction functions.
TypeScript
67.1K
5 points
R
Rednote MCP
RedNote MCP is a tool that provides services for accessing Xiaohongshu content. It supports functions such as authentication management, keyword - based note search, and command - line initialization, and can access note content via URL.
TypeScript
12.4K
4.5 points
P
Perplexity MCP
Certified
An MCP server based on the Perplexity AI API, providing web search functionality for the Claude desktop client.
Python
15.7K
4.1 points
E
Exa Web Search
Certified
The Exa MCP Server is a server that provides web search capabilities for AI assistants (such as Claude), enabling real-time and secure web information retrieval through the Exa AI Search API.
TypeScript
28.7K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
23.8K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
15.7K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
45.0K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
14.8K
4.5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
46.0K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
19.3K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
15.0K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
29.5K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase