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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.