velog

velog is a plugin for Claude Code from milcho0604/velog-mcp. Its token cost is not measured, scanned A, original, MIT.

A Claude Code plugin for Velog, a Korean blogging platform for developers. It can browse, search, and inspect Velog content, and it can create posts with writing defaulting to drafts or private posts.

In plain words
What is it for?
Reading Velog posts, finding trending content, checking blog statistics, drafting or publishing articles, and adding diagrams or cover images.
Why use it?
It connects coding-agent work with Velog while keeping publishing cautious by requiring an explicit public-publishing choice. It can also render diagrams, sequence diagrams, and cover images for posts, with local Chrome needed for those uploads.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add milcho0604/velog-mcp
agentmods
npx agentmods add plugins/milcho0604/velog-mcp/velog
Clone the repo
git clone --depth 1 https://github.com/milcho0604/velog-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for velog

README.md
[![agentmods](https://agentmods.dev/badge/plugins/milcho0604/velog-mcp/velog.svg)](https://agentmods.dev/plugins/milcho0604/velog-mcp/velog)
Your own site
<a href="https://agentmods.dev/plugins/milcho0604/velog-mcp/velog"><img src="https://agentmods.dev/badge/plugins/milcho0604/velog-mcp/velog.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

velog 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 5d 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.

plugins/velog/.claude-plugin/plugin.json · 51 lines

What it actually says

{
	"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
	"name": "velog",
	"displayName": "Velog",
	"version": "0.8.9",
	"description": "Read and write Velog (velog.io), the Korean developer blogging platform. Browse, search, trending, and blog stats work with no auth. Writing defaults to drafts and private posts — public publishing is opt-in at install. Also renders diagrams, sequence diagrams, and cover images for your posts and uploads them (needs local Chrome). 벨로그 글을 읽고 쓰고, 다이어그램과 시퀀스 다이어그램과 표지도 그려서 올립니다.",
	"author": {
		"name": "Changhyun Kim",
		"url": "https://github.com/milcho0604"
	},
	"homepage": "https://github.com/milcho0604/velog-mcp#readme",
	"repository": "https://github.com/milcho0604/velog-mcp",
	"license": "MIT",
	"keywords": [
		"velog",
		"blog",
		"blogging",
		"writing",
		"publishing",
		"korean",
		"markdown",
		"diagram",
		"cover-image"
	],
	"userConfig": {
		"refresh_token": {
			"type": "string",
			"title": "Velog refresh token",
			"description": "velog.io 로그인 → F12 → Application → Cookies → refresh_token 값. 벨로그에 공개 쓰기 API 가 없어서 이 방법뿐입니다. 이 서버가 이 값을 싣는 목적지는 velog.io 뿐이고 저장소 테스트(A6)가 그걸 강제합니다 — 다만 값은 서버를 실행하는 npx/npm 프로세스의 환경에도 놓입니다(README 참고). 없이 설치하면 읽기 전용으로 동작합니다.",
			"sensitive": true
		},
		"allow_public": {
			"type": "boolean",
			"title": "공개 발행 허용",
			"description": "끄면 초안과 비공개 발행까지만 됩니다. 공개 발행은 RSS·검색·구독메일로 나간 뒤에는 지워도 회수가 안 되므로 기본은 꺼짐입니다.",
			"default": false
		},
		"allow_profile": {
			"type": "boolean",
			"title": "프로필 수정 허용",
			"description": "이름·한줄소개·블로그 제목 등을 고칠 수 있게 합니다. 위험해서가 아니라 헷갈려서 막아둡니다 — 프로필의 '소개'와 글의 '요약'은 이름이 비슷해서, 꺼두면 잘못 짚어도 사고가 안 납니다.",
			"default": false
		},
		"chrome_path": {
			"type": "file",
			"title": "크롬 실행 파일 경로 (선택)",
			"description": "다이어그램·표지 그리기에 로컬 크롬이 필요합니다. 표준 위치에 설치돼 있으면 비워두세요 — 자동으로 찾습니다. 지정하면 자동 탐색을 하지 않고 이 파일만 씁니다."
		}
	}
}
Contents

What it installs

The manifest is a name and a version. 1 MCP server travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.

Changes

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.

  1. 5d ago First seen · 51 lines scan A 88eaf3876321

Subscribe to this mod's changes

velog is a plugin published in the GitHub repository milcho0604/velog-mcp (0 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.