Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pranciskus/newsmcp --skill skillgit clone --depth 1 https://github.com/pranciskus/newsmcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pranciskus/newsmcp/skill)<a href="https://agentmods.dev/skills/pranciskus/newsmcp/skill"><img src="https://agentmods.dev/badge/skills/pranciskus/newsmcp/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pranciskus/newsmcp/skill"><img src="https://agentmods.dev/badge/skills/pranciskus/newsmcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00029 | $0.01941 |
| Opus 5.5 | $0.00012 | $0.00776 |
| Sonnet 5.5 | $0.00006 | $0.00388 |
| Haiku 4.5 | $0.00003 | $0.00194 |
Grade A, and why
newsmcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
World News Skill
Get real-time world news from an AI-powered news aggregation service. Stories are clustered into events (deduplicated across multiple sources), summarized, classified by topic, and tagged by geography.
No API key required. No authentication. Just call the API.
Why This Is Different
- Events, not articles — individual articles are clustered into stories, so you get one summary per story instead of 20 duplicates
- Pre-summarized — every event has an AI-generated summary, no need to read full articles
- Classified — 12 topic categories and 100+ geographic regions
- Importance signals —
sources_count(how many outlets covered it) andimpact_score(AI-assessed significance) - Multi-source — each event lists all source articles with titles, URLs, and domains
API Base URL
https://newsmcp.io/v1
Endpoints
1. Get News Events
curl -s "https://newsmcp.io/v1/news/?hours=24&per_page=10&order_by=-sources_count"
Parameters:
| Parameter | Type | Default | Description |
|---|---|---|---|
hours |
int | 24 | Time window (1-168, i.e. up to 7 days) |
topics |
string | — | Comma-separated topic slugs (e.g. politics,military) |
geo |
string | — | Comma-separated geo slugs (e.g. europe,united-states) |
page |
int | 1 | Page number |
per_page |
int | 20 | Results per page (max 50) |
order_by |
string | -sources_count |
Sort field. Options: sources_count, entries_count, impact_score, first_seen_at, last_seen_at (prefix - for descending) |
Response shape:
{
"events": [
{
"id": "uuid",
"summary": "AI-generated event summary",
"topics": ["politics", "military"],
"geo": ["europe", "ukraine"],
"entries_count": 15,
"sources_count": 8,
"first_seen_at": "2026-03-03T10:00:00Z",
"last_seen_at": "2026-03-03T14:00:00Z",
"impact_score": 4,
"entries": [
{
"title": "Article headline",
"url": "https://example.com/article",
"domain": "example.com",
"published_at": "2026-03-03T12:00:00Z"
}
]
}
],
"total": 42,
"page": 1,
"per_page": 10
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 198 lines · 29 tokens per session scan A 61bed2e6e990
newsmcp is a skill published in the GitHub repository pranciskus/newsmcp (33 stars, last pushed 8mo ago), licensed MIT. It adds 29 tokens to every session and 1,941 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
newsmcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| newsmcppranciskus/newsmcp | Skill | 33 | 8mo ago | MIT | A | 29 | Claude Code, Codex |
| swagjmagar/swag-mcp | Skill | 7 | 4d ago | MIT | A | 118 | Claude Code |
| visit-binary-banyapdarche/model-wellness | Skill | 2 | 14d ago | MIT | A | 93 | Claude Code, Codex |
| umt-mcpMarkgatcha/universal-mcp-toolkit | Skill | 16 | 3d ago | MIT | B | 89 | Claude Code |
| cortex-snippetsdinglebear-ai/cortex | Skill | 4 | 3d ago | AGPL-3.0 | A | 51 | Claude Code, Codex |
| using-cortexdinglebear-ai/cortex | Skill | 4 | 3d ago | AGPL-3.0 | A | 58 | Claude Code, Codex |
| install-cortexdinglebear-ai/cortex | Skill | 4 | 3d ago | AGPL-3.0 | A | 51 | Claude Code, Codex |