NCCN Monitor
Monitors all 92 NCCN clinical practice guidelines for version updates, downloads updated PDFs, extracts change notes, and generates AI-powered summaries via MCP protocol.
README
NCCN Monitor
Monitor NCCN clinical guideline updates and get notified when new versions are published.
NCCN (National Comprehensive Cancer Network) publishes clinical practice guidelines for 92 cancer types and supportive care topics. These guidelines are updated frequently, and keeping track of changes is important for oncologists, researchers, and pharmaceutical professionals.
NCCN Monitor tracks version changes across all 92 NCCN professional guidelines, downloads updated PDFs, extracts update notes, and generates AI-powered change summaries — all accessible through the MCP protocol for integration with OpenClaw or any MCP-compatible AI assistant.
Features
- Complete coverage — monitors all 92 NCCN professional guidelines across 4 categories (Cancer by Type, Screening, Supportive Care, Specific Populations)
- Version change detection — compares current versions against stored state, detects updates
- PDF download + analysis — logs into NCCN (free registration), downloads updated PDFs, extracts update notes from the first few pages
- AI-powered summaries — generates structured prompts for LLM-based change analysis (Chinese or English)
- Health monitoring — detects silent scraping failures and alerts after consecutive errors
- Chinese language support — all 92 guidelines have Chinese names and aliases for fuzzy search
- Watch list management — configure which guidelines to monitor via natural language (Chinese or English)
- On-demand PDF download — download any guideline PDF by name (Chinese or English fuzzy search)
- Version archiving — automatically archive old versions when updates are detected, with standardized filenames (
NCCN_GastricCancer_2026.V2_EN.pdf) - Change timeline — view the full version history for any guideline
Quick Start
Prerequisites
Install
git clone https://github.com/fshaan/nccn-monitor.git
cd nccn-monitor
uv venv --python 3.13 .venv
source .venv/bin/activate
uv pip install -e ".[dev]"
Configure
cp config.example.yaml config.yaml
Edit config.yaml to set your NCCN credentials and watch list. Or use environment variables:
export NCCN_USERNAME="your_email@example.com"
export NCCN_PASSWORD="your_password"
Run
# Start the MCP server (stdio transport)
python -m nccn_monitor.server
# Run unit tests
python -m pytest tests/ -v
# Run integration test (needs NCCN credentials)
python tests/integration_test.py
MCP Tools
| Tool | Description |
|---|---|
check_updates |
Check all guidelines for version updates, download PDFs, generate change reports |
get_status |
Return health status, last check time, tracked guideline count |
list_guidelines |
List all 92 NCCN guidelines with versions and Chinese names |
find_guideline |
Fuzzy search by Chinese name, English name, or abbreviation |
update_watch_list |
Add/remove/set monitored guidelines via natural language |
browse_guidelines |
Browse all guidelines organized by category |
download_guideline |
Download a specific guideline PDF by name (Chinese/English), archive it |
get_guideline_history |
View version history and change timeline for a guideline |
OpenClaw Integration
Native Plugin (recommended)
Install as an OpenClaw plugin for direct tool registration:
# Copy plugin to OpenClaw extensions
cp -r openclaw-plugin ~/.openclaw/extensions/nccn-monitor
cd ~/.openclaw/extensions/nccn-monitor && npm install
Then add to your ~/.openclaw/openclaw.json under plugins.entries:
{
"nccn-monitor": {
"enabled": true,
"config": {
"pythonPath": "/path/to/nccn-monitor/.venv/bin/python",
"projectDir": "/path/to/nccn-monitor"
}
}
}
After openclaw gateway restart, 8 tools (nccn_check_updates, nccn_get_status, etc.) appear natively in OpenClaw.
Note: Only keys declared in
openclaw.plugin.jsonconfigSchema are allowed in the plugin config. Settings likearchive_dirgo in the project'sconfig.yaml, not inopenclaw.json.
Via mcporter (alternative)
If you prefer using mcporter as middleware:
npx mcporter config add nccn-monitor --transport stdio \
--command "/path/to/.venv/bin/python" --args "-m" --args "nccn_monitor.server"
Then use the mcporter skill in OpenClaw to call tools.
Cron scheduling
Set up a daily cron job in OpenClaw to call nccn_check_updates (or check_updates via mcporter) for automatic monitoring.
Architecture
OpenClaw (cron + notifications)
│
│ MCP Protocol (stdio)
▼
┌─────────────────────────────────────┐
│ NCCN Monitor MCP Server │
│ │
│ scraper ──→ state ──→ notifier │
│ │ │
│ ▼ (on version change) │
│ downloader ──→ analyzer │
│ (NCCN login) (PDF extraction) │
└─────────────────────────────────────┘
Credits
- NCCN login and PDF download logic adapted from gscfwid/NCCN_guidelines_MCP
- Built with FastMCP for MCP server implementation
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。