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 isnow890/naver-search-mcp --skill naver-search-mcpgit clone --depth 1 https://github.com/isnow890/naver-search-mcpWrote 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/isnow890/naver-search-mcp/naver-search-mcp)<a href="https://agentmods.dev/skills/isnow890/naver-search-mcp/naver-search-mcp"><img src="https://agentmods.dev/badge/skills/isnow890/naver-search-mcp/naver-search-mcp/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/isnow890/naver-search-mcp/naver-search-mcp"><img src="https://agentmods.dev/badge/skills/isnow890/naver-search-mcp/naver-search-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 15 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 49 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 61 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00051 | $0.01336 |
| Opus 5 | $0.00026 | $0.00668 |
| Sonnet 5 | $0.00010 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
naver-search-mcp scanned grade A with 0 findings 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 12d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Naver Search MCP
Use this skill for Korean search tasks that are better served by Naver than general web search: news, blogs, cafe posts, images, Knowledge iN, encyclopedia, local places, and DataLab trend analysis (search trends and shopping insight).
한국 웹 검색, 네이버 뉴스/블로그/카페/이미지/지식iN/백과사전/지역 검색, 네이버 DataLab 검색어 트렌드와 쇼핑인사이트 분석에 사용합니다.
github: https://github.com/isnow890/naver-search-mcp
This skill wraps the published MCP server:
npx -y @isnow890/naver-search-mcp
Setup
- Install from ClawHub with
openclaw skills install naver-search-mcp. - Supply one credential pair — never a partial mix of the two:
- NAVER API HUB (forward path, recommended):
NCP_APIGW_API_KEY_IDandNCP_APIGW_API_KEY. - Naver Developers (legacy, existing keys only):
NAVER_CLIENT_IDandNAVER_CLIENT_SECRET. Developers Center stops accepting new applications on 2026-07-31; existing keys keep working until 2027-06-30.
- NAVER API HUB (forward path, recommended):
- In OpenClaw,
apiKeymaps toNAVER_CLIENT_SECRETbecause this skill declaresprimaryEnv: NAVER_CLIENT_SECRET(kept for backward compatibility with existing legacy installs). HUB users should set bothNCP_APIGW_API_KEY_IDandNCP_APIGW_API_KEYas explicit environment variables instead of usingapiKey, sinceapiKeyonly ever maps to the legacy secret. - Provide the other variable in the pair through the skill
envconfig or OpenClaw environment (legacy users:NAVER_CLIENT_ID). - Restart OpenClaw or the Gateway after changing credentials.
- Do not ask users to clone this repository for normal use; cloning is only for development.
Example OpenClaw config (Naver Developers, legacy, using apiKey):
{
"skills": {
"entries": {
"naver-search-mcp": {
"enabled": true,
"apiKey": "your_naver_client_secret",
"env": {
"NAVER_CLIENT_ID": "your_naver_client_id"
}
}
}
}
}
Example OpenClaw config (NAVER API HUB — set both variables explicitly, do not use apiKey):
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.
- 12d ago First seen · 114 lines · 51 tokens per session scan A 16561dd7760e
naver-search-mcp is a skill published in the GitHub repository isnow890/naver-search-mcp (85 stars, last pushed 3d ago), licensed MIT. It adds 51 tokens to every session and 1,336 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
batch-analysis
Overnight batch execution of queued analysis designs. Generates marimo notebooks (8-cell contract), executes headlessly, self-reviews results, records journal events, and produces a morning summary for human triage. Use when: running overnight analysis, processing batch queue, scheduling unattended analysis, reviewing…
analysis-design
A guided workflow for writing analysis-design documents: short records that state a data question, its hypothesis, and how to investigate it. EDA means exploring data to find patterns and test ideas.
rq-problematization
Generates impactful research questions using Alvesson & Sandberg's (2011) problematization framework. Collects prior research, surfaces the assumptions a literature takes for granted across five types, and dialectically challenges them via a devil's-advocate subagent — moving beyond gap-spotting to…
analysis-framing
An analysis-planning guide that explores existing data, notes, and past analyses to help define a clear direction for investigation.
analysis-journal
A reasoning journal for recording how an analysis develops, including observations, evidence, decisions, questions, and competing explanations.
analysis-revision
A guided workflow for revising an analysis design after reviewers leave comments. It reads review feedback, tracks each comment, and helps address the comments one by one.