netxops
Run the following command in DeepSeek Harness:
dsh plugin install hansjone/netxops
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install hansjone/netxops in your terminal to install the plugin; the full source lives at https://github.com/hansjone/netxops
About this plugin
Running network operations inside DeepSeek Harness used to mean spinning up a separate MCP service, hand-crafting REST calls, and stitching together alert notifications with ad-hoc scripts. netxops collapses that entire pipeline into a single plugin: native netx__* REST tools are exposed out of the box, so you only need to configure the API URL and token—no local pip install of netx_mcp, no OpenClaw dependency, no extra host process.
The plugin ships a live-status card and an optional key-alarm push channel that keeps a WSS connection open to the Netx /v1/integrations/dsh-alarm/ws hub. Alerts flow back into the current DSH session and can simultaneously be delivered to WhatsApp or any IM supported by Netx (a botId and targetId are all you need). An auto-installed Netx Ops Agent preset—complete with persona, UME, and managed-NE skills—lands in ~/.dsh/.agent-presets on first host activation, ready to pick in any new session.
It is aimed at network engineers who already run a Netx platform and want to fold day-to-day operations and incident response into the conversational flow of DeepSeek Harness, especially teams that prefer not to maintain a standalone MCP service.
Use Cases
- Call Netx REST APIs directly from a DSH session for device inspection and config push
- Receive key alerts in real time via WSS into the DSH session and WhatsApp or IM
- Use the preset Netx Ops Agent for UME and managed-NE daily operations
Best For
- Network engineers who run a Netx platform and want ops workflows embedded in DeepSeek Harness
- Small to mid-size teams that prefer not to maintain a standalone MCP service
- SRE or NOC on-call staff who need network alerts bridged into IM channels
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.