@fotor-ai/dsh-fotor-plugin

中文文档
0.8.0发布于 2026/11/04Apache-2.0ES Module构建来源已验证近 30 天下载 2691

Connect to the Fotor MCP service to create images, video and audio.

原始使用文档
文档目录10 节
  1. Verification scope
  2. DeepSeek Harness
  3. DeepSeek Harness installation
  4. DeepSeek Harness configuration and connection
  5. DeepSeek Harness updates
  6. DeepSeek Harness source selection and removal
  7. Workflows
  8. Bundle contents
  9. License
  10. Skill-local references

Fotor for DeepSeek Harness

Requires stable Node 24.2.0 or later within 24.x, or stable Node 26.x. Current acceptance uses Linux DeepSeek Harness Web 0.2.1-rc.3. Earlier rc.2 results retain their original scope. Use the release's recorded results for the exact tested host, runtime and installation route.

Fotor logo

Version Release channel Apache-2.0 license

DeepSeek Harness

Create images, video and audio with Fotor through DeepSeek Harness Web and an automatically installed MCP bridge dependency.

FieldValue
Bundle@fotor-ai/dsh-fotor-plugin
Version0.8.0
Release channelproduction
Service environmentproduction
MCP endpointhttps://mcp.fotor.com/mcp
Declared host range>=0.2.1-rc.2 <0.3.0-0
Host baselineLinux DeepSeek Harness Web 0.2.1-rc.3
Bridgemcp-remote 0.15.2
Node range>=24.2.0 <25.0.0 || 26.x, stable versions
LicenseApache-2.0

Verification scope

Package checks cover files, references, and configuration. Verify installation, MCP authorization and calls, website login, credit links, uploads, and media execution separately in the selected host and environment. A release or model query does not establish successful website login or completed media results.

The Bundle supplies two small native Host adapters that configure the host-owned components automatically. The bridge is acquired by the package manager and owns OAuth. npm artifacts carry its full runtime dependency tree; Git installs download the dependency. Complete support requires real controlled reauthorization recovery as well as installation, calls, website access and restart reuse; consult the evidence for the installed release. Media execution and expiry-driven refresh are not established by static checks.

DeepSeek Harness

DeepSeek Harness is abbreviated as dsh in commands and native identifiers.

DeepSeek Harness installation

Production release

First verify that the selected revision contains the DeepSeek Harness Bundle. Install this scoped package and its pinned bridge dependency to the chosen profile. Select Web Enable now or load the CLI profile; both components then configure automatically unless explicit user settings disable them.

dsh plugin --profile web add "git+https://github.com/fotor-ai/dsh-fotor-plugin.git" --ignore-scripts

This is the standalone root Bundle for https://github.com/fotor-ai/dsh-fotor-plugin. Use its root Git source only after the selected channel contains this version. The multi-platform repository documents this external source; it no longer distributes new DeepSeek Harness packages. Existing subdirectory installations require a one-way native source migration.

The Bundle identity is @fotor-ai/dsh-fotor-plugin. After the corresponding npm channel is published, its alternative is dsh plugin --profile web add "@fotor-ai/dsh-fotor-plugin" --ignore-scripts (production) or dsh plugin --profile web add "@fotor-ai/dsh-fotor-plugin@next" --ignore-scripts (test). Verify the resolved version and select one source only. Bare-name npm installation follows latest.

Installation automatically obtains mcp-remote 0.15.2. Git sources download it through the host package manager; npm artifacts carry its complete locked runtime tree. Fotor skills remain script-free. No installation hook runs code; host activation starts connection and may open browser consent. Node is not bundled.

Follow the complete installation guide:

  1. Check Linux DeepSeek Harness Web 0.2.1-rc.3 and stable Node 24.2.0 or later within 24.x, or 26.x.
  2. Install one source with lifecycle scripts disabled.
  3. In Web, click Enable now after installation; in CLI, start the selected profile. Both enabled-by-default adapters resolve their paths automatically.
  4. Complete browser consent when required; existing valid authorization is reused.
  5. Verify actual skill and tool discovery. Configure the model account separately; website access is a separate request.

The declared host range is >=0.2.1-rc.2 <0.3.0-0; matching versions are not automatically verified. Desktop, headless and ACP require separate acceptance.

DeepSeek Harness configuration and connection

The native adapters resolve skills, Node and the pinned bridge at activation. Existing explicit overrides and disabled states take precedence. The full configuration example is optional and never auto-applied. Overrides replace complete config objects. Keep default skill roots and native MCP reconnect disabled.

Credentials remain outside the installation, in the configured MCP_REMOTE_CONFIG_DIR or the active profile's dedicated Fotor directory. Follow authentication instructions. The adapter runs client discovery, closes that client and its callback, then starts the native MCP proxy. User consent remains required; disabling MCP cancels its connection task.

Use the user's confirmed daily ordinary browser. MCP-only requests do not request website links; website requests prepare the browser, open the original handoff once through native permission controls, and wait for actual page confirmation. An existing login is not a first-login result.

DeepSeek Harness updates

For a recorded Git source:

dsh plugin --profile web update @fotor-ai/dsh-fotor-plugin --ignore-scripts
dsh plugin --profile web why @fotor-ai/dsh-fotor-plugin

For a recorded npm source, replace <target-version> with the approved, published version:

dsh plugin --profile web update "@fotor-ai/dsh-fotor-plugin@<target-version>" --ignore-scripts

During historical 0.6.0-test.2 acceptance, immediate @next updates retained 0.6.0-test.1; exact-version native updates passed. An unqualified update can also retain the saved version. Neither @latest update success nor eventual success after 24 hours is established. Use the maintenance procedure; keep release-age protection and request separate approval for any exact-version exception. Never apply an npm selector to a Git source as an ordinary update.

Verify the source, version, files and actual skill/bridge directories in a new process. Preserve profile/store, credentials and connection parameters. If installation used a custom --store-dir, pass that same argument to updates and removal. A zero exit code with the old version is not an upgrade; cache clearing or reinstall does not turn it into a pass.

DeepSeek Harness source selection and removal

Production release

First verify that the selected revision contains the DeepSeek Harness Bundle. Install this scoped package and its pinned bridge dependency to the chosen profile. Select Web Enable now or load the CLI profile; both components then configure automatically unless explicit user settings disable them. Record the old source and scope, remove only this Fotor Bundle through native controls, then add the selected source. Preserve the external credential directory and valid overrides; verify automatically resolved paths when enabling the new package.

dsh plugin --profile web add "git+https://github.com/fotor-ai/dsh-fotor-plugin.git" --ignore-scripts

Test release

First verify that the selected revision contains the DeepSeek Harness Bundle. Install this scoped package and its pinned bridge dependency to the chosen profile. Select Web Enable now or load the CLI profile; both components then configure automatically unless explicit user settings disable them. Record the old source and scope, remove only this Fotor Bundle through native controls, then add the selected source. Preserve the external credential directory and valid overrides; verify automatically resolved paths when enabling the new package.

dsh plugin --profile web add "git+https://github.com/fotor-ai/dsh-fotor-plugin.git#release/test" --ignore-scripts

Legacy fotor and scoped packages are different identities. Stop Fotor components and record old source/profile/store/paths and explicit overrides, then remove the old Bundle with dsh plugin --profile web remove fotor --config.ignore-scripts=true. Add one scoped source. Version 0.6.1 resolves its runtime paths automatically unless explicit overrides apply; preserve valid values and correct or remove only obsolete path overrides through native configuration. Preserve disabled settings, model settings, the external credential directory, callback/security parameters and daily browser state; do not automatically remove the old external bridge.

GitHub/npm switching uses the same explicit remove/add sequence, with @fotor-ai/dsh-fotor-plugin as the removal target. Keep one installed source and one component pair. Ordinary update does not rename packages or switch sources. See maintenance.

Uninstall retains external credentials but does not revoke server consent. Same-profile reinstall can reuse accepted authorization; enabling still establishes a new connection that requires actual discovery/query verification. Expired or rejected credentials may need new consent. Reinstall is not evidence of a successful native upgrade.

Workflows

Start with connection and model discovery, then select the skill matching the request. Follow media preparation for local references and credits to query your own Fotor credit balance. These instructions do not establish host acceptance of every media operation.

Bundle contents

  • package.json and cordis.patch.yml: the Bundle and two enabled-by-default adapters.
  • configuration.example.yml: optional complete legacy override; never auto-applied.
  • INSTALL.md: self-contained setup and migration guide.
  • package-lock.json: reviewed npm release-build input in Git snapshots; not a host-level Git dependency lock.
  • runtime/: automatic configuration and cancellable connection ownership; no installation hooks.
  • npm artifacts additionally contain the pinned third-party runtime; Fotor skills remain script-free.
  • .github/: Git snapshot publication tooling, excluded from installed packages.
  • skills/, including each skill's references/: shared workflows and DeepSeek Harness bridge/browser guidance.
  • assets/logo.svg, README.md and LICENSE: package-local documentation and branding.

License

Apache-2.0

Skill-local references

Audio workflows cover soundtrack composition, new tracks, song editing, speech, podcasts and vocal separation. Consult the installed audio skill when available. The host deadline and generated bridge header/body timeouts default to 300 seconds. See tool call timeouts for scopes and overrides. A deadline is not confirmation that a task failed; preserve any known ID without automatic resubmission.

Every packaged skill carries four generated documents in its own references/ directory, including this platform's authentication guide. Read them as needed; complete runtime documentation does not install or configure MCP.

版本与发布记录

@fotor-ai/dsh-fotor-plugin 共发布 11 个版本,首次发布于 2026/10/22;过去 12 个月发布了 11 个版本。最新版本附带 npm provenance 构建来源证明,可追溯到公开的 CI 构建记录。

版本发布日期距今
0.8.0latest2026/11/0411 天前
0.8.0-test.1next2026/11/0411 天前
0.6.12026/10/2719 天前
0.6.1-test.22026/10/2620 天前
0.6.1-test.12026/10/2620 天前
0.6.02026/10/2323 天前

关于 @fotor-ai/dsh-fotor-plugin 的常见问题

@fotor-ai/dsh-fotor-plugin 是什么?

Connect to the Fotor MCP service to create images, video and audio.

如何安装 @fotor-ai/dsh-fotor-plugin?

在项目目录运行 npm install @fotor-ai/dsh-fotor-plugin,或使用 pnpm add / yarn add / bun add。

@fotor-ai/dsh-fotor-plugin 支持 TypeScript 吗?

该包的 package.json 没有声明类型入口。需要类型提示时,可以在 npm 上查找社区维护的 @types/fotor-ai__dsh-fotor-plugin 是否存在。

@fotor-ai/dsh-fotor-plugin 支持 ESM 还是 CommonJS?

以 ES Module 形式发布,推荐使用 import 引入。在 CommonJS 项目中,Node.js 20.19+ / 22.12+ 可以直接 require() 不含顶层 await 的 ES Module,更早的版本需要改用动态 import()。

@fotor-ai/dsh-fotor-plugin 需要什么版本的 Node.js?

package.json 的 engines 字段要求 Node.js >=24.2.0 <25.0.0 || 26.x。版本不符时 npm 默认只给出警告,开启 engine-strict 后会拒绝安装。

@fotor-ai/dsh-fotor-plugin 可以商用吗?

@fotor-ai/dsh-fotor-plugin 使用 Apache-2.0 许可。宽松许可:允许商业使用、修改和再分发,并附带明确的专利授权;分发时需保留许可与 NOTICE 文件,修改过的文件要注明改动。以上为概括,不构成法律意见,请以许可原文为准。

@fotor-ai/dsh-fotor-plugin 的下载量有多少?

根据 npm 官方下载统计,@fotor-ai/dsh-fotor-plugin 在 2026/10/16 – 2026/11/14 这 30 天内被下载 2,691 次,日均约 90 次。下载量会把 CI 构建、镜像同步和作为其他包依赖的安装一并计入,适合横向比较热度,不能直接等同于使用人数。

@fotor-ai/dsh-fotor-plugin 还在维护吗?

最新版本 0.8.0 发布于 2026/11/04(11 天前);至今共发布 11 个版本,其中过去 12 个月发布了 11 个;首次发布于 2026/10/22。发布频率只是参考信号:功能稳定的工具可能很少需要更新,建议结合源码仓库的 issue 和提交记录判断。