SamurAIGPT/dsh-plugin-muapi
DeepSeek Harness插件,将MuApi的100多种图像/视频/音频生成模型作为智能体工具开放。
Project Overview项目介绍
This repository is a native plugin built exclusively for DeepSeek Harness (DSH). It adds a muapi_generate tool to the DSH agent that connects to MuAPI, a unified API service that grants access to over 100 generative AI models for creating images, videos, audio, and 3D assets. All supported models are accessed through a single API key, so users do not need to manage separate credentials for each individual model provider. To install the plugin, run the command dsh plugin add @dsh-plugin/dsh-plugin-muapi in your terminal. After installation completes, you will need to configure your API key before first use.
After installation, navigate to DSH’s Settings menu, find the muapi configuration section, and paste your MuAPI API key, which you can create at muapi.ai/access-keys. When enabled, the plugin exposes the muapi_generate tool to the DSH agent, which takes two core arguments: a model slug and an input parameter object for the model. For example, a user might pass flux-schnell-image as the model slug and { "prompt": "a serene mountain lake at dawn" } as the input. You can browse the full catalog of supported models at muapi.ai/playground, where each model’s exact parameters are documented in an llms.txt file.
The tool works by sending a POST request to MuAPI’s endpoint to create the generation job, then polling the result endpoint at a set interval until the job completes or fails, then returns the output URLs to the DSH agent. The plugin includes multiple configurable options beyond the required API key, including whether the tool is enabled, the API base URL, the polling interval in milliseconds, and the maximum timeout for a generation job. By default, the polling interval is set to 3000 milliseconds (3 seconds) and the maximum timeout is 600000 milliseconds (10 minutes). This plugin is released under the open-source MIT license, with no cost for the plugin itself, though MuAPI may charge for API access per your usage plan.
本仓库是专为 DeepSeek Harness(DSH)开发的原生插件,用于为 DSH 代理添加调用 MuAPI 多模态生成服务的能力。MuAPI 是一个统一生成 API,聚合了超过 100 种图像、视频、音频、3D 生成模型,包括 Flux、Veo 3、Kling、Seedance、Suno 等主流模型,所有模型都通过统一的 API Key 认证调用。
安装方式非常简单,只需要在终端执行 dsh plugin add @dsh-plugin/dsh-plugin-muapi 命令,完成安装后进入 DSH 的设置页面找到 muapi 配置项,填入从 muapi.ai/access-keys 创建获取的 API Key 即可启用该工具。使用时 DSH 代理会调用 muapi_generate 工具,指定模型标识和对应输入参数即可发起生成请求。
插件支持多项自定义配置,包括是否启用工具、API 基地址、轮询结果的间隔、任务超时时间等,默认轮询间隔为 3 秒,最大超时时间为 10 分钟。用户可以在 muapi.ai/playground 浏览完整模型列表,每个模型的具体参数也可以在对应页面的 llms.txt 文件中查看。本插件采用 MIT 许可证开源。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-plugin-muapi(SamurAIGPT/dsh-plugin-muapi)
仓库:https://github.com/SamurAIGPT/dsh-plugin-muapi
本站详情页:https://www.yhbd.top/plugins/samuraigpt-dsh-plugin-muapi/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 3 · 最近提交 2026-08-17 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 3 stars - very few users, little community feedback星标只有 3,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin add @dsh-plugin/dsh-plugin-muapi
把 SamurAIGPT/dsh-plugin-muapi 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-plugin-muapi
A DeepSeek Harness plugin that gives the agent a muapi_generate tool for MuApi — a unified API for 100+ image, video, audio, and 3D generation models (Flux, Veo 3, Kling, Seedance, Suno, and more) behind a single x-api-key.
Install
dsh plugin add @dsh-plugin/dsh-plugin-muapi
Then, in Settings → muapi, set your API key credential (create one at muapi.ai/access-keys).
What it does
Registers one tool, muapi_generate:
model— a MuApi model slug, e.g.flux-schnell-imageorkling-v2-1-image-to-video. Browse the full catalog at muapi.ai/playground; each model's exact parameters are documented athttps://muapi.ai/playground/{model}/llms.txt.input— that model's parameter object, e.g.{ "prompt": "a serene mountain lake at dawn" }.
The tool submits the job (POST https://api.muapi.ai/api/v1/{model}), polls GET https://api.muapi.ai/api/v1/predictions/{request_id}/result until it completes or fails, and returns the output URLs.
Configuration
| Setting | Default | Description |
|---|---|---|
tool.enabled |
true |
Expose the tool to the agent. |
tool.apiKeyEnv |
— | Credential reference for your MuApi API key. |
tool.baseUrl |
https://api.muapi.ai/api/v1 |
API base URL. |
tool.pollIntervalMs |
3000 |
Delay between result polls. |
tool.timeoutMs |
600000 |
Max time to wait for a job to complete. |
License
MIT
nexu-io/open-design
Devin-AXIS/iPolloWork
liustack/modlens
Alisa0808/vox-director
EthanYoQ/AI-Novel-Writer
Anionex/agent-vision-toolkit
ysr666/dsh-vision-router
tong-io/tongflow