Native DeepSeek Harness plugin for IsingQ: guided QUBO modeling and validation on-device, then user-confirmed remote solving.
Install
# from npm (prebuilt)
dsh plugin --profile web add @ising-tech/isingq-dsh-plugin
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:ising-tech/isingq-toolkit#path:/packages/dsh-plugin
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
Native IsingQ integration for DeepSeek Harness: QUBO modeling, validation, and cloud or private-network local solving, using @ising-tech/isingq-core inside the DSH process.
简体中文 · English
This guide covers 0.9.x, which registers 21 tools. Install only versions actually published on npm, then verify the loaded version. A source checkout does not establish release availability.
Install
In the app
In DeepSeek Harness, open Plugins → Add plugin, enter @ising-tech/isingq-dsh-plugin, and click Install. Follow the on-screen prompts; no terminal is needed.
Command line
Install into the Profile you actually use:
dsh plugin --profile <profile> add @ising-tech/isingq-dsh-plugin
For the macOS desktop app, fully quit it first, use its bundled CLI at /Applications/DeepSeek Harness.app/Contents/Resources/runtime/cli/bin/dsh, and select the active desktop Profile. Use the actual Profile for other entrypoints.
Reopen and verify the loaded Plugin version and its tools. npm installs published versions; local device support in this guide requires 0.9.x. Avoid enabling an IsingQ MCP bridge alongside the native Plugin in the same Profile.
Requirements: Node.js 18.17+; DSH and @deepseek-ai/dsh-tools >=0.1.0-rc.7 <0.3.0-0. The development validation baseline is DSH 0.2.2-rc.1.
Basic use
Describe your problem to the Agent. Review the variables, objective, constraints, and matrix summary, then choose a target at solve confirmation and explicitly approve submission:
- Cloud: browse public models and suitability advice. For actual submission, create a personal API Key in the cloud console, configure it through the private
isingq_api_key_setupprompt, and choose a compute voucher or account balance. - Local: ask to add/manage local solvers; enter a device name and service address and test the connection. Multiple devices are supported, without a cloud API Key, voucher, or account balance.
Advice does not block your target choice. Saving a local connection does not submit a task. Each call record keeps its actual target and viewing location, pointing to the cloud console or a locally accessible address.
Keep API Keys out of chat, tool arguments, Profile configuration, and logs. Cloud tasks send the matrix to IsingQ; local tasks send it to the selected device.
Updates, removal, and help
Keep the original Profile and distribution when updating. Use DSH's plugin management to install a published version, reload, and verify the loaded version. Toolkit's built-in version check provides notices only.
Remove with:
dsh plugin --profile <profile> remove @ising-tech/isingq-dsh-plugin
- Missing tools: check the Profile and duplicate MCP bridges; reload, then restart if needed.
- Version conflict: check the DSH and SDK compatibility range above.
- Local connection failure: check the network and service address, then test on the management page.
- Cloud authentication failure: replace the Key through the private prompt; never paste it into chat.
Toolkit guide · Integration and developer acceptance · Solver target API · Apache-2.0
Links
More in this category
Tencent/WeKnora#dsh-weknora★ 37918
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.
DayuanJiang/next-ai-draw-io#dsh-plugin★ 37097
Draws draw.io diagrams in DeepSeek Harness through the next-ai-drawio MCP server: the link in the reply opens a live preview in the right sidebar, you can edit the diagram by hand, and each AI change is a version you can restore. Node.js 18+; npx downloads the MCP server on first use.
superdesigndev/treg★ 8650
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.
T-Auto/dsh-ops★ 5964
Provides bash, PowerShell 7, and high-performance Rust tools for DSH on Windows to reduce token usage.
sixtysevenlf/dsh-blender-plugin★ 2216
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.
helloHub1212/dsh-windows-mcp★ 2002
Bridges the CursorTouch/Windows-MCP desktop automation server into DSH through the official MCP client bridge, registering its screenshot, UI tree snapshot, mouse and keyboard input, clipboard, process and registry tools as mcp__windows__* tools for the model, and adds a windows_mcp_doctor diagnostic tool. Computer Use is off by default and is switched on from the plugin panel.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.