Skillget

nats-news-analysis

mcp
Security Audit
Pass
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 12 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool acts as an MCP server that fetches news articles, extracts their content, matches specified keywords, and automatically saves the curated results directly to a user's Raindrop.io account.

Security Assessment
The primary function of this server relies on making external network requests to scrape news websites and interact with the Raindrop.io API. To authenticate with Raindrop.io, the tool will require you to provide an API token, which means it interacts with your personal account credentials. The automated code scan of 12 files found no dangerous patterns, hardcoded secrets, or requests for risky system permissions. The code does not appear to execute arbitrary shell commands. Overall risk is rated as Low.

Quality Assessment
The project is licensed under the standard MIT license, making it freely available for integration. It appears to be highly maintained, with the most recent code push occurring just today. While it currently lacks a README file to guide users through setup, the repository has garnered 12 GitHub stars, indicating a baseline level of community interest and basic trust among developers.

Verdict
Safe to use, though users should be prepared to configure API tokens securely and manage the tool without the benefit of standard setup documentation.
SUMMARY

Find news articles, retrieves their content, matches keywords, and puts results on Raindrop.io

README.md

Title: Personal News Analysis
summary: Automatically find relevant news from the Web.

Systematically retrieves online news articles, enriches them, scans them for keywords and sends hits to raindrop.io. All analysis components are loosely-coupled with NATS.io queues, which also allows scaling single-core-CPU-intensive components easily.

Open In Draw.io

The system has the following NATS queues:

  1. feed-urls - URLs of RSS feeds.
  2. article-urls - URLs of individual articles of RSS feeds.
  3. news - News texts and their metadata.
  4. match-urls - URLs of positive matching articles.

The outcomes of this system are:

  1. A Raindrop.io collection with articles matching to keywords.
  2. An Azure AI Search index prepared for hybrid search on news.
  3. A Grafana dashboard with metrics.
  4. An MCP-Server that allows consuming 1 and 2 with an agentic LLM (such as Roo Code).

Involved services

All services are orchestrated and scaled with compose.yml.

Custom services

Third party services

Message queue for scaling

Instead of blocking the application with a single core keyword matching operation, or even trying to build a complex multi-threading keyword matching, we are using the scale option of docker compose to run multiple single-core keyword matching components in parallel, wired together with the message queue. This allows us to keep individual components super straight-forward and easy to maintain.

Keyword matching containers, scaled up

One core per keyword matching

Observability

A typical Prometheus-Loki-Grafana stack is used to monitor application metrics and statistics.

NATS server stats are made available to Prometheus via Prometheus NATS Exporter.

Keyword-matcher-containers use zerolog and expose their logs to Loki using the Docker Loki logging driver.

A Grafana dashboard ships with the source of the repository.

Comparing Python with Golang

As one of the core components responsible for the main analysis task, keyword-matcher has been ported from Python to Golang, for fun and research purposes. Both implementations of keyword-matcher can play alongside or even to compete with each other:

NAME                                                 CPU %     MEM USAGE / LIMIT
loki                                                 1.33%     74.55MiB / 7.667GiB
nats-news-analysis_fullfeedrss_1                     0.00%     76.68MiB / 7.667GiB
nats-news-analysis_fullfeedrss_2                     0.01%     70.62MiB / 7.667GiB
nats-news-analysis_grafana_1                         0.17%     35.95MiB / 7.667GiB
nats-news-analysis_keyword-matcher-go_1              0.00%     8.051MiB / 7.667GiB
nats-news-analysis_keyword-matcher-go_2              0.00%     8.422MiB / 7.667GiB
nats-news-analysis_keyword-matcher-go_3              0.00%     8.781MiB / 7.667GiB
nats-news-analysis_keyword-matcher-go_4              0.00%     8.059MiB / 7.667GiB
nats-news-analysis_keyword-matcher-python_1          0.00%     22.64MiB / 7.667GiB
nats-news-analysis_keyword-matcher-python_2          0.00%     23.21MiB / 7.667GiB
nats-news-analysis_keyword-matcher-python_3          0.00%     24.23MiB / 7.667GiB
nats-news-analysis_keyword-matcher-python_4          0.00%     23.8MiB / 7.667GiB
nats-news-analysis_loadbalancer_1                    0.00%     2.316MiB / 7.667GiB
nats-news-analysis_nats-server_1                     1.34%     92.97MiB / 7.667GiB
nats-news-analysis_natsexporter_1                    0.03%     7.41MiB / 7.667GiB
nats-news-analysis_pocket-integration_1              0.00%     18.41MiB / 7.667GiB
nats-news-analysis_prometheus_1                      0.00%     37.22MiB / 7.667GiB
nats-news-analysis_rss-article-url-feeder-go-1st_1   0.05%     15.32MiB / 7.667GiB
nats-news-analysis_rss-article-url-feeder-go-2nd_1   11.46%    12.95MiB / 7.667GiB

Here are some interesting stats from Docker and Loki, collected during regular operation:

Metric Python Golang Comparison
Docker image size 424MB 6.09MB Go impl. is ~70x smaller
Memory consumption 23,8MiB 8,33MiB Go impl. needs ~3x less memory
LoC 447 485 Python impl. has ~8% less lines

Reviews (0)

No results found