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
Create images, video and audio with Fotor through DeepSeek Harness Web and an automatically installed MCP bridge dependency.
| Field | Value |
|---|
| Bundle | @fotor-ai/dsh-fotor-plugin |
| Version | 0.8.0 |
| Release channel | production |
| Service environment | production |
| MCP endpoint | https://mcp.fotor.com/mcp |
| Declared host range | >=0.2.1-rc.2 <0.3.0-0 |
| Host baseline | Linux DeepSeek Harness Web 0.2.1-rc.3 |
| Bridge | mcp-remote 0.15.2 |
| Node range | >=24.2.0 <25.0.0 || 26.x, stable versions |
| License | Apache-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:
- Check Linux DeepSeek Harness Web
0.2.1-rc.3 and stable Node 24.2.0 or later within 24.x, or 26.x.
- Install one source with lifecycle scripts disabled.
- In Web, click Enable now after installation; in CLI, start the selected profile. Both enabled-by-default adapters resolve their paths automatically.
- Complete browser consent when required; existing valid authorization is reused.
- 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.
