dsh-nekowhale-stickers
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dsh-nekowhale-stickers我有点累了想摸鱼,来张大肥鱼表情包"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
表情包作者:B站 可以叫我云大人/雾雪 · kiriyuki.com 制作 · 欢迎约原稿同款表情包! 套组:大肥鱼 · 大肥鱼和GPT娘
✨ 特性
Related MCP server: cove-sticker-mcp
🖼️ 模板示例
👥 角色
🚀 安装
dsh plugin --profile web add dsh-nekowhale-stickers重启 dsh web 即可。dsh 0.2 也可以在网页侧栏 插件 → 添加插件 里填 dsh-nekowhale-stickers。也可以安装本地打包的 .tgz(pnpm pack)。
⚙️ 配置
最简单的方式:dsh 网页侧栏打开 插件 → 大肥鱼表情包(dsh 0.1.x 在 设置 → 插件 → 大肥鱼表情包),改完点保存,立即生效、无需重启。
也可以在 profile 的 cordis.patch.yml 里写默认值,网页里的设置会覆盖它:
- id: nekowhale-stickers
config:
promptMode: hint # skill | hint | index | off
frequency: normal # rare | normal | often
blacklist: [tag:舌吻] # id、文件名、编号、名字,或 pack: / tag: / emotion: / group: 前缀项 | 默认 | 说明 |
| 两套 | 要使用的套组 |
|
|
|
|
|
|
|
| 常驻提示的多少; |
|
| 允许 agent 用 |
|
| 模板开关;与网站一致的屏蔽词过滤 |
|
| 把图片附给模型看(消耗图像 token) |
|
| 网页界面里显示大肥鱼桌宠; |
|
| 桌宠大小(高度,像素)、对话气泡(关掉可少加载约 1.5 MB) |
🧰 工具
工具 | 作用 |
| 按情绪 / 场景找表情,每条一行: |
| 返回一行 Markdown 图片,模型原样放进回复;传情绪词则随机取一张 |
| 用模板生成表情 |
| 浏览、详情、开关、模式、出处、同步 |
🤝 在其他插件和框架里使用
提供四种通用接口:
cordis 服务(dsh 内的其他插件,如 QQ 桥接):
inject: ['stickers'],然后ctx.stickers.search()/.file()/.url()/.render()。回复标记:纯文本回复里写
[sticker:名字],或[sticker:开心]这类情绪词(同类随机取一张),桥接插件用parseReply()拆成文字与图片。NapCat / OneBot 发 GIF 时给图片段加sub_type: 1才会按表情显示。MCP(LangBot、NoneBot / AstrBot 的 LLM 插件、Claude / Cursor 类客户端等):
{ "command": "npx", "args": ["-y", "dsh-nekowhale-stickers", "mcp"] }工具返回本地路径和公网 URL,由宿主自己发文件。
数据与 CLI(任何语言):
meta/nekowhale.json(线上https://kiriyuki.com/meme/kit/nekowhale.json),或npx dsh-nekowhale-stickers search 摸鱼 npx dsh-nekowhale-stickers index npx dsh-nekowhale-stickers render 大肥鱼举牌 今天也要开心 -o sign.gif
亦可基于本仓库重新开发。
🛠️ 开发
pnpm install && pnpm build
node tools/dev/smoke.mjs /tmp/data # 用假 ctx 跑一遍全部工具tools/annotate/:标注流程,抽帧拼图 → 多模态模型逐张标注 →build_meta.py合并成meta/nekowhale.json。tools/art/:头图与展示图的合成脚本(背景底板 + 真实表情帧 + Live2D 立绘);成品图片由 kiriyuki.com 托管。
📄 许可
代码采用 Apache-2.0:允许对代码进行二次修改,修改或重新发布同类功能必须保留 NOTICE,即标明本仓库地址与表情包作者链接。
知识库数据(meta/ 等,见 LICENSE-ASSETS)采用 CC BY-NC 4.0:允许对资源进行二次分发,但必须保留原作者链接和网址,且禁止付费提供或用于其他商业用途。
表情包基础形象和模板由 可以叫我云大人/雾雪 制作;网页桌宠由 kiriyuki.com 提供。
This server cannot be deployed
Maintenance
Related MCP Connectors
Search, install and submit Markdown skills for AI agents; private Brain files when signed in.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Search photos and video moments by visual meaning, people, dates, and folders across local libraries, Apple Photos, and OneDrive. Manage collections, groups, favorites, people, and duplicate review. Synced metadata remains searchable while the desktop is offline; local and Apple Photos media access needs the owning device online with remote access enabled. OneDrive media can be accessed directly from the cloud. OAuth or Bearer API keys. Paid Cloud Access required; hosted visual search uses prepaid credits. Text-in-image search is semantic matching, not guaranteed exact OCR. Setup: https://organizewith.ai/en/guides/connect-ai-assistants
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI to send expressive stickers based on conversation context, with a built-in UI for managing stickers.58MIT
- AlicenseNot gradedqualityBmaintenanceLocal-first custom sticker library for MCP agents, enabling image import, auto-tagging, search, and context-aware retrieval via standard MCP tools.35MIT
- FlicenseNot gradedqualityCmaintenanceEnables users to upload and tag stickers and GIFs through a web page, then lets Claude browse, select, add, retag, or delete them so it can send an image matching the mood of a conversation. Returns ready-to-paste markdown image links that render in markdown-capable chat interfaces.3-
- AlicenseNot gradedqualityBmaintenanceEnables users to import, tag, search, and retrieve custom stickers by context through MCP, with optional vision model tagging and backup/restore, all local-first and portable.MIT