Skip to main content
Glama
Sign In
xhs-image-mcp

xhs-image-mcp

by dthinkr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

XHS Image MCP

将文章/文本转换为小红书风格图片卡片的 MCP Server，支持 AI 生成封面图。

功能

  • 智能分页 - 使用浏览器实际测量自动分页，确保内容不溢出

  • 4种主题 - minimal / elegant / warm / dark

  • 3种比例 - 3:4 (推荐) / 1:1 / 4:3

  • AI 封面 - 使用 Gemini 根据文章内容生成艺术封面（设置 API Key 后自动启用）

  • Markdown 支持 - 直接读取 .md 文件并自动清理格式

  • MCP 协议 - 可与 Claude Desktop / Claude Code 集成

Related MCP server: Xiaohongshu (RedBook) MCP Server

v1.1.0 更新

  • ✨ 智能 AI 封面 - 设置 GEMINI_API_KEY 后自动生成 AI 封面，无需手动开启

  • 🔧 自动分页优化 - 使用浏览器实际测量替代字数估算，彻底解决内容溢出问题

  • 📐 AI 封面空间适配 - 第一页自动为 AI 封面横幅预留空间

小红书尺寸

比例

尺寸

说明

3:4

1080×1440px

推荐，占据最大屏幕空间

1:1

1080×1080px

方形，适合产品展示

4:3

1080×810px

横版，适合风景照

安装

npm install -g xhs-image-mcp
npx playwright install chromium

或从源码安装：

git clone https://github.com/dthinkr/xhs-image-mcp.git
cd xhs-image-mcp
npm install
npx playwright install chromium
npm run build

使用

MCP Server 配置

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "xhs-image": {
      "command": "npx",
      "args": ["-y", "xhs-image-mcp"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Claude Code (~/.claude/settings.json):

{
  "mcpServers": {
    "xhs-image": {
      "command": "npx",
      "args": ["-y", "xhs-image-mcp"]
    }
  }
}

测试

npm test

MCP Tools

text_to_images

将文本转换为图片序列。

参数

类型

必填

说明

text

string

Yes

文本内容

title

string

标题（用于封面）

theme

string

minimal / elegant / warm / dark

ratio

string

3:4 / 1:1 / 4:3

fontSize

string

small / medium / large

showCover

boolean

是否生成封面页

generateAiCover

boolean

使用 AI 生成封面图（设置 API Key 后默认开启，传 false 可禁用）

outputDir

string

输出目录，图片保存为 PNG

file_to_images

将 Markdown/文本文件转换为图片。

参数

类型

必填

说明

filePath

string

Yes

文件路径 (.md/.txt)

title

string

覆盖自动提取的标题

theme

string

主题

generateAiCover

boolean

AI 封面（设置 API Key 后默认开启，传 false 可禁用）

outputDir

string

输出目录

estimate_pages

估算页数（不生成图片）。

list_themes

列出所有可用主题。

主题

主题

风格

适用场景

minimal

白底黑字，简约

知识干货、教程

elegant

米白衬线，书卷气

小说、散文、诗歌

warm

暖色渐变，卡片式

情感生活、分享

dark

深色护眼

夜间阅读、科技

环境变量

变量

说明

GEMINI_API_KEY

Google Gemini API Key，用于 AI 封面生成（设置后自动启用 AI 封面）

获取 API Key: https://aistudio.google.com/app/apikey

License

MIT

Available Tools

4 tools
estimate_pagesA

Estimate how many pages the text will be split into without generating images

Inputs: text (required), ratio, fontSize, charsPerPage.

file_to_imagesA

Convert a local markdown or text file to a series of images. Supports .md, .txt, .text files. Automatically extracts title from the first # heading in markdown files. Cleans up markdown formatting for cleaner text display.

Inputs: filePath (required), ratio, theme, title, +5 more.

list_themesA

List all available themes with descriptions

Inputs: no named parameters.

text_to_imagesB

Convert text content to a series of images with Xiaohongshu (小红书) style themes.

Supported themes:

  • minimal: Clean white background, good for knowledge/tips content

  • elegant: Warm beige with serif font, good for novels/essays

  • warm: Warm gradient with card style, good for lifestyle/emotional content

  • dark: Dark mode, eye-friendly for night reading

Image ratios:

  • 3:4 (1080x1440): Best for Xiaohongshu feed, takes most screen space

  • 1:1 (1080x1080): Square format

  • 4:3 (1080x810): Landscape format

Inputs: text (required), ratio, theme, title, +5 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: estimating page count, listing themes, converting text to images, and converting files to images. There is no overlap in functionality, making selection unambiguous.

    Naming Consistency4/5

    Most tool names follow a descriptive pattern with underscores, but there is a mix of verb_noun (estimate_pages, list_themes) and noun_to_noun (text_to_images, file_to_images). This is a minor deviation from a fully consistent naming convention.

    Tool Count5/5

    With just 4 tools, the set is well-scoped for its purpose. Each tool is essential and contributes to the workflow without redundancy or bloat.

    Completeness5/5

    The tool set covers the full conversion lifecycle: estimating output size, selecting themes, and converting from two input methods (text and file). No critical operations are missing for the stated purpose.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers