DSH Marketplace

dsh-blender-plugin

sixtysevenlf/dsh-blender-plugin

Lets a DSH agent drive a local Blender over a direct TCP channel with 15 tools: viewport frames, custom-angle renders, Python execution, headless and job offload, transaction rollback, and a planning layer of 228 ops across 34 families.

1,45656PythonBSD-3-ClauseSource

Install

Add dsh-blender-plugin to DeepSeek Harness

Install into

via GitHub · GitHub source

Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.

What happened when we ran it

Installed cleanly when we ran it

Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 6d agoon DeepSeek Harness 0.2.1-rc.5.

Show it in your README

install verified — dshmarketplace

For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.

Due diligence

Before you install dsh-blender-plugin

  • Source of record: sixtysevenlf/dsh-blender-plugin — present in the community registry that DSH's own plugin market installs from.
  • Licensed under BSD-3-Clause.

Security

What installing dsh-blender-plugin runs

Build scripts

No build script was blocked in our run.

Source: our sandbox install on DeepSeek Harness 0.2.1-rc.5, 6d ago.

Install hooks

package.json declares no preinstall, install or postinstall script.

Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.

README mentions

shell commands (bash, exec, spawn …)

Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.

Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.

The AI take

What it is — Gives a DSH agent a live handle on the Blender instance on this machine: look, edit, run Python, render, or hand work to a background session.

Who it is for — You are using a DSH agent to check an assembly or build a parametric surface in a Blender window on the same computer, and you need the agent to read the viewport and a reference image, then re-render after each edit. Skip the plugin when the agent process cannot reach Blender on this machine; the channel listens on loopback.

Watch out — A clean profile accepted the install and the harness registered the plugin. GUI work still needs the bundled bridge addon enabled on Blender 4.x or 5.x first (or the persistent worker if there is no GUI), plus Node.js 20 or newer. The install runs shell commands, and no other Blender bridge is supported.

The verdict — Leave it off for a handful of one-off object edits; only keep the channel if that same .blend is already open all day under DSH.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.

What dsh-blender-plugin does

Geometric meshes flow through a local conduit, inspection lenses and rollback loops into verified exports.

dsh-blender-plugin is a DeepSeek Harness plugin that connects an agent to a local Blender session through a direct TCP channel. It is designed for building, inspecting, validating and exporting 3D scenes while the agent works against the Blender instance in front of it.

DeepSeek Harness uses the bundled addon/dsh_blender_bridge.py Blender addon for the GUI route. The addon listens on 127.0.0.1:9876; the plugin can inspect scenes, execute Python in a persistent Blender kernel, capture viewport or custom-angle frames, and send selected objects or collections into the current draft. A persistent headless worker provides code execution and Workbench frames when no GUI is available. The tool set also covers reference-image measurement, parametric surface construction, assembly checks and repairs, exports, background jobs, batch validation, rollback and delivery gates.

This is intended for agents operating on local Blender projects, including modelling, scene validation and export workflows. It is a poor fit when Blender is unavailable, when a remote Blender connection is required, or when the bundled addon cannot be installed for GUI use; headless operation still needs the Blender executable. The plugin exposes a terminal surface through Python execution, one-shot headless scripts and background jobs, so it can modify the local Blender scene and write exported assets with the agent’s permissions. Use the bundled addon only; the README explicitly instructs users not to install MCP for Blender or another Blender addon.

dsh-blender-plugin documentation

Configuring dsh-blender-plugin

DeepSeek Harness loads dsh-blender-plugin as a profile bundle. The profile’s package.json uses the dependency key @dsh-external/dsh-blender-plugin and adds the same package to dsh.profile.bundles. The repository includes the built lib directory, so a normal checkout is ready to use. Rebuilding after changes to src/ uses DSH_CHECKOUT with scripts/build.sh.

The Blender-side connection is provided by addon/dsh_blender_bridge.py. Install and enable that file in Blender, open the 3D View’s N panel, and click Connect. The addon listens on 127.0.0.1:9876.

Commands and checks

DeepSeek Harness exposes Blender operations including blender_viewport and blender_rt_worker.

  • blender_viewport with op="launch" starts Blender, enables the addon and connects automatically.
  • blender_rt_worker with op="start" starts a persistent headless worker, taking a worker name.
  • blender_rt_worker with op="see" requests a frame for that named worker.
  • curl http://127.0.0.1:9877/health checks the service.
  • curl http://127.0.0.1:9877/doctor checks the GUI route; acceptance requires kind equal to ok.

A headless worker returning a frame confirms the fallback route. The GUI doctor’s bpy round-trip is expected to be unreachable in headless-only mode.

Requirements for dsh-blender-plugin

DeepSeek Harness must be installed and working. The backend requires Node.js 20 or newer. Blender 4.x or 5.x is supported; GUI mode requires the bundled addon, while headless mode requires only the Blender executable. An optional DeepSeek Harness source checkout is needed only to rebuild the plugin.

Behaviour and limits

The normal path is GUI-first and interactive. Headless mode is a fallback that supplies Workbench frames rather than a GUI. Reference measurements return pixel units when no scale is known instead of inventing millimetres. The plugin can export GLB, FBX or OBJ in documented workflows, and can produce a turntable MP4. It is local-only as documented: the addon uses 127.0.0.1, and the README does not document a remote Blender transport.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to dsh-blender-plugin

33k

Four read-only tools over a WeKnora knowledge base: list knowledge bases, hybrid passage search, reassemble one document's chunks in order, and WeKnora's own cited RAG or ReAct-agent answer with a resumable session id.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceGo24d ago

AI review

dsh-weknora

What it is — dsh-weknora provides four read-only tools to operate WeKnora knowledge base for DeepSeek Harness.

Who it is for — When using ReAct-agent in DeepSeek Harness to process WeKnora knowledge base, these tools can provide corresponding capabilities. If you do not use DeepSeek Harness for agent tool calls but rely on other integration methods, you do not need this plugin.

Watch out — Needs to provide API key or token. Will execute shell commands. No obvious pitfalls found.

The verdict — I will install it because it provides WeKnora knowledge base's RAG or ReAct-agent answer function.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

treg

superdesigndev

6.0k

Tool catalog for agents: search ~2,600 external endpoints (SEO and SERP, backlinks, social, people and company enrichment, ad libraries, scraping) by the task you want done, read each one's parameters and per-call price, then call it with the credential injected server-side. Ships the skill plus an MCP row that stays disabled until TREG_TOKEN is set.

Installed cleanly when we ran it

GitHub sourcePython12d ago

AI review

treg

What it is — Lets an agent find ~2,600 third-party endpoints by the job to be done, read parameters and the per-call price, then invoke them with credentials injected on the server. Ships a skill.

Who it is for — Running DeepSeek inside DeepSeek Harness on competitive or lead research, when the agent needs SERP, backlink, or company-enrichment calls and you hold none of those vendor accounts. It is the wrong shape if secrets and upstream traffic must leave only through your own network, with no external proxy injecting auth.

Watch out — It installed cleanly in a fresh profile and was registered. A GitHub source install runs shell commands. Catalog usage is billed per call (from a cent; a new verified account gets $1.00 once); calls that use your own keys are not metered. MCP stays off until TREG_TOKEN is set.

The verdict — I'll add it. I want the monthly vendor seats collapsed into one per-call bill, and I accept treg as that counterparty.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details
1.4k

Anime Garden for DSH: search anime torrent resources from 動漫花園, 蜜柑计划, 萌番组 and ANi inside DSH — via chat, a sidebar panel with fansub and type filters, a seasonal calendar, and an in-app floating player.

No one-line install — this plugin lives inside a larger repository and publishes no npm package.

GitHub sourceTypeScriptyesterday

AI review

AnimeGarden

What it is — Brings anime torrents from 動漫花園, 蜜柑计划, 萌番组, and ANi into DSH, searchable in chat or a sidebar, plus a season calendar and a floating player.

Who it is for — You are inside a DeepSeek Harness agent picking this season’s release and still leave the session to filter by fansub and type. If MCP or the HTTP API already feeds that index in another toolchain, skip this plugin.

Watch out — This listing has no one-line install; the plugin lives in a repo subdirectory and has to be wired in by hand. It runs shell commands. No sandbox run is on record, so there are no measured pitfalls.

The verdict — I’d add it only if torrent hunting already happens inside DSH most weeks.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

dsh-plugin

TencentCloudBase

1.1k

Tencent CloudBase backend for DeepSeek Harness — scaffold and deploy full-stack apps from chat, render query results as table cards with paging, sorting and CSV export, preview a deployment on its domain, and call the CloudBase MCP toolset (`mcp__cloudbase__*`) with device-code login.

Installed cleanly when we ran it

npm packageTypeScript26d ago

AI review

dsh-plugin

What it is — DeepSeek Harness plugin integrating Tencent CloudBase backend. Supports scaffolding and deploying full-stack apps from chat, rendering query results as table cards, and calling CloudBase MCP toolset.

Who it is for — Suitable for users developing full-stack applications with DeepSeek Harness who need cloud backend scaffolding and deployment support.

Those not requiring integration with Tencent CloudBase databases, storage, or deployments can skip it.

Watch out — After npm install, it registers successfully in a fresh profile and gets enabled by Harness. It executes shell commands but sandbox testing passes. No obvious issues found.

The verdict — If you're already running backend services on Tencent CloudBase, I would install it for the direct MCP toolset and deployment preview integration.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details
842

Chrome sidebar extension that lets DSH operate your browser directly, no vision capabilities required.

Installed cleanly when we ran it

GitHub sourceTypeScript1mo ago

AI review

dsh-browser

What it is — Allow DeepSeek Harness to directly control your open browser tabs.

Who it is for — If you want DeepSeek Harness to operate pages you have open in your browser for automation tasks, install this plugin. If your tasks only involve multimodal dialogue without browser tools, you don't need to install it.

Watch out — Installation requires running a script and manually allowing the extension load; an API key is needed. Sandbox test passed. The benchmark completed 30/30 tasks with mean latency of 5.32s.

The verdict — I would install it because it is faster than the Playwright baseline with fewer tool calls.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
2Details

anysearch-dsh

anysearch-team

664

AnySearch-powered real-time web and vertical search provider for DeepSeek Harness.

Installed cleanly when we ran it

npm packageTypeScript25d ago

AI review

anysearch-dsh

What it is — The @anysearch/anysearch-dsh plugin integrates AnySearch with DeepSeek Harness to provide real-time web and vertical search.

Who it is for — When using DeepSeek Harness to perform AI agent tasks that require real-time web and vertical search support, this plugin is suitable for installation. If you are not using the DeepSeek Harness framework to execute tasks, this plugin does not apply.

Watch out — Sandbox test passed: successfully installed in a fresh profile and registered by Harness. Requires Node.js 22.19 or Node.js 24+ and pnpm 11.7. No obvious issues found.

The verdict — I would install it because it supports anonymous access without an API key but configuring one provides 1,000 free search calls per day.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
Source