Article Research Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Article Research Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP server for article/tutorial research during agent planning — dev.to search, deduped ranked briefs, methodology aligned with Hermes deep-research.
Agent docs: CONTEXT.md, HERMES.md, docs/adr/, research/
| Source | Id |
|---|---|
| dev.to | devto |
| Hacker News (Algolia) | hn |
| RSS/Atom (configurable) | rss |
Default: devto + hn. Add rss via sources=["devto","hn","rss"].
RSS feeds — ARTICLE_RESEARCH_RSS_FEEDS (comma-separated URLs) or built-in defaults (dev.to mcp/ai tags, hnrss frontpage).
Set OpenAI-compatible API (e.g. LAN Ollama):
export OPENAI_COMPAT_BASE_URL=http://localhost:11434/v1
export OPENAI_COMPAT_API_KEY=ollama
export OPENAI_COMPAT_MODEL=lfm2.5:latestsearch_articles(..., score_with_llm=true)build_topic_brief(..., depth=deep) auto-enables LLM scoring when env is setWithout env vars, deterministic ranking only.
| Tool | Purpose |
|---|---|
plan_article_research | Step list + tool sequence for quick/standard/deep |
get_research_methodology | Depth levels, source tiers, checklist |
search_articles | Multi-source search (devto + hn) |
build_topic_brief | Dedupe + rank + markdown brief |
get_article | Full body by source + id |
save_research_note | Write ~/research/<slug>/ARTICLE_BRIEF.md |
list_article_sources | Supported sources + LLM config status |
article-research://methodologyarticle-research://plan/{topic}ARTICLE_DAILY_TOPICS="mcp,agent planning" uv run python scripts/daily_brief.pyWrites ~/research/daily-briefs/<date>-<topic>/BRIEF.md. Hermes cron: research/daily_article_brief.sh at 08:00 UTC (job 6ab3a0a34eb2), delivers summary to this Slack DM when stdout is non-empty.
cd /path/to/article-research-mcp
uv sync
uv run article-research-mcpcatalogue.json)Entry name: article_research (see DynamicMCPProxy catalogue.json).
cd /path/to/article-research-mcp
uv sync
printf 'y\n' | hermes mcp add article_research \
--command uv \
--args --directory,/path/to/article-research-mcp,run,article-research-mcpNew session or /reload-mcp + /reset.
| Variable | Default |
|---|---|
ARTICLE_RESEARCH_ROOT | ~/research |
OPENAI_COMPAT_BASE_URL | — (e.g. http://localhost:11434/v1) |
OPENAI_COMPAT_API_KEY | ollama |
OPENAI_COMPAT_MODEL | lfm2.5:latest |
devto-mcp-server — thin dev.to-only server (superseded for planning use this umbrella)deep-research — multi-lens synthesis after briefsMIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.