WenyanSAFE
文颜 MCP Server 可以让 AI 自动将 Markdown 文章排版后发布至微信公众号。
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/@wenyan-md/mcp) [](LICENSE) [](https://hub.docker.com/r/caol64/wenyan-mcp) [](https://github.com/caol64/wenyan-mcp)
简介
[文颜(Wenyan)](https://wenyan.yuzhi.tech) 是一款多平台 Markdown 排版与发布工具,支持将 Markdown 一键转换并发布至:
- 微信公众号
- 知乎
- 今日头条
- 以及其它内容平台(持续扩展中)
文颜的目标是:让写作者专注内容,而不是排版和平台适配。
文颜的不同版本
文颜目前提供多种形态,覆盖不同使用场景:
- macOS App Store 版 - MAC 桌面应用
- 跨平台桌面版 - Windows/Linux
- CLI 版本 - 命令行 / CI 自动化发布
- 👉 MCP 版本 - 本项目
文颜 MCP Server 是什么?
简单来说,它打通了“AI 写作”与“公众号发文”的通道。
基于 MCP 协议,Claude Desktop 等 AI 客户端现在可以直接调用文颜(Wenyan)的排版引擎。写完文章后,不需要再去第三方编辑器里来回复制粘贴,直接让 AI 帮你排版并塞进微信草稿箱。
核心特性:
- 绕过排版工具:AI 生成的 Markdown 直接转成微信富文本并上传,省去中间步骤。
- 对话式排版:直接打字跟 AI 说“换个橙色风格主题”,样式自动生效。
- 不出窗口完成闭环:在同一个聊天框里,顺滑搞定“想选题 -> 写文章 -> 调排版 -> 存草稿”的所有操作。
实战演示:
功能特性
- 一键发布 Markdown 到微信公众号草稿箱
- 自动上传本地图片与封面
- 支持远程 Server 发布(绕过 IP 白名单限制)
- 内置多套精美排版主题
- 支持自定义主题
- 提供标准 MCP Tool 接口
- 支持 AI 自动调用:
- 渲染 Markdown
- 主题管理
- 发布草稿
快速开始
安装
npm install -g @wenyan-md/mcp `
8fa3ef404275OBSERVED · 2026-09-25Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp --env LLM_API_KEY=${LLM_API_KEY} -- npx -y @wenyan-md/[email protected]{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@wenyan-md/[email protected]"
],
"env": {
"LLM_API_KEY": "${LLM_API_KEY}"
}
}
}
}Exposed tools (4)
2 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
list_themes | read | List the themes compatible with the |
publish_article | write | Format a Markdown article using a selected theme and publish it to |
register_theme | read | Register a custom theme compatible with the |
remove_theme | destructive | Remove a custom theme compatible with the |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
remove_theme
@wenyan-md/core, form-data-encoder, formdata-node, jsdom, zod, @eslint/js, @modelcontextprotocol/inspector, @types/node
Gates applied: no_behavioural_pass.
8fa3ef404275full audit observations/trust-audit/mcp-server/caol64__wenyan.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-25 | 8fa3ef404275 | SAFE | B | 89 | first audit |
Questions
What is the Wenyan MCP server?
文颜 MCP Server 可以让 AI 自动将 Markdown 文章排版后发布至微信公众号。
What tools does Wenyan expose?
4 in total: 2 read-only, 1 that write, and 1 that can delete or overwrite (remove_theme). Every one is listed on this page with its risk.
Is Wenyan safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Wenyan need?
It reads LLM_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Wenyan run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @wenyan-md/mcp at 2.0.4.
How current is this page?
The grade is for one exact copy of the source (8fa3ef404275), read on 2026-09-25. The repository is watched and re-audited when it changes.