dsh-plugin
DayuanJiang/next-ai-draw-iodsh 的 draw.io 绘图插件:通过 next-ai-drawio MCP 服务器作图,点回复里的链接在右侧栏打开实时预览,可以手动修改图,AI 的每次修改都是可以恢复的版本。需 Node.js 18+,首次使用由 npx 下载 MCP 服务器。
DSH host plugin that adds the cursor_agent tool: run the Cursor CLI
(cursor-agent) headlessly on a task in a workspace, straight from any DSH
agent session.
Cursor runs its own agent loop (reads/edits files, calls tools) and the tool
returns its final message plus the Cursor chat id, so a run can be continued
later with resume.
# from a DSH session with the plugin manager available — git source, pinned by the market index
plugin_manager install_bundle target="git+https://github.com/qyjqio/dsh-cursor-toolkit.git#<commit>&path:/packages/dsh-cursor-cli"
# or plain pnpm, inside a DSH profile directory
pnpm add "git+https://github.com/qyjqio/dsh-cursor-toolkit.git#<commit>&path:/packages/dsh-cursor-cli"
Then enable the bundle (include:cursor-cli) in Settings → Plugins, or add
@qyjqio/dsh-cursor-cli to the profile's dsh.profile.bundles.
cursor-agent --version,
cursor-agent login.PATH, ~/.local/bin,
/usr/local/bin, /usr/bin (override with the executable config field).--trust.| name | type | meaning |
|---|---|---|
prompt | string (required) | Task for Cursor; be explicit about goal and done criteria |
cwd | string | Workspace dir; defaults to the session working directory, accepts ~ |
mode | agent | plan | ask | agent edits/runs tools; plan/ask are read-only |
model | string | Cursor model id (e.g. auto, composer-2.5); default = CLI default |
force | boolean | Pass --force (auto-approve tool calls). Default true; ignored for read-only modes |
resume | string | Cursor chat id returned by a previous run |
continueSession | boolean | Continue the most recent chat in the workspace |
timeoutSeconds | integer 1..3600 | Run budget; default 900 |
{ ok, result, cwd, mode, truncated, timedOut, aborted,
sessionId?, model?, durationMs?, exitCode?, stderr? }
ok is false when the process exits non-zero, Cursor reports is_error, or the
run times out / is aborted. The rendered card shows the final message plus a
footer with session id, model, mode, duration and cwd.
Optional bundle config (all values are defaults in code when omitted):
| key | default | meaning |
|---|---|---|
executable | auto-detected | Path to cursor-agent |
allowForce | true | Whether force may be passed at all |
model | CLI default | Default model when the call omits one |
maxOutputChars | 60000 | Result truncation limit |
timeoutMs | 900000 | Default timeout |
cursor_agent({ prompt: "Fix the failing test in tests/auth.spec.ts" })cursor_agent({ prompt: "Review src/api for error handling gaps", mode: "plan" })cursor_agent({ prompt: "Now apply the plan", resume: "<sessionId>" })CURSOR_API_KEY is honored.cwd is validated before spawning; a missing directory fails fast instead of
letting Cursor create one.