Shunwang Tech Connector for AI agents.
10 live capabilities
Manage edge computing nodes and GPU clusters with natural language.
Waiting for input…
Why people use Shunwang Tech
Shunwang Tech for Managing Distributed GPU Clusters
With this Connector, you just tell your agent to check the health of the GPU cluster. It pulls the data from Shunwang Tech, summarizes the load, and alerts you only if something is actually broken. You go from clicking through menus to just getting answers.
What Vinkius changes
You get a natural language interface for managing complex edge computing hardware.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Scaling AI Inference
An AI dev asks the agent to deploy a model to the 'Huzhou' cluster using a specific image.
- Real-world use case 02
Emergency Node Recovery
An admin notices a hung node and asks the agent to send a reboot command.
- Real-world use case 03
Capacity Planning
A manager asks for a summary of GPU usage across all clusters to see if they need more hardware.
Complete set · 10capabilities
The complete Shunwang Tech capability set.
These are the exact actions your AI can choose when you ask it to work with Shunwang Tech.
01—04
4 capabilities in this set.
Part of 10 available through Shunwang Tech.
- 01 Capability
List images
View all available system images for your nodes. This helps you see what software environments you can deploy.
- 02 Capability
Get gpu specs
Check the hardware specifications for your GPUs. This is useful for planning your inference capacity.
- 03 Capability
Create task
Launch a new computing task on your infrastructure. This lets you deploy new jobs to specific clusters quickly.
- 04 Capability
Get node
Pull detailed information for a specific node. Use this to deep dive into the status of a single machine.
05—07
3 capabilities in this set.
Part of 10 available through Shunwang Tech.
- 05 Capability
Get resource usage
See a summary of current resource consumption. It helps you monitor how hard your clusters are working.
- 06 Capability
List clusters
Browse all available computing clusters in your network. Use this to organize your distributed infrastructure.
- 07 Capability
List nodes
Get a full list of all computing nodes in your network. Use this to see which hardware is currently online.
08—10
3 capabilities in this set.
Part of 10 available through Shunwang Tech.
- 08 Capability
List tasks
See every computing task currently running across your clusters. It helps you track active jobs at a glance.
- 09 Capability
Send node command
Send a direct management command to a specific node. You can use this to reboot or shut down hardware remotely.
- 10 Capability
Stop task
Halt a running computing task immediately. Use this to free up resources from jobs that are no longer needed.
Set up in minutes
One URL. Then ask Shunwang Tech to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Shunwang Tech from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_bgiyuAWhRzWrIFnn1swCL5IcEpCA8FYUUwp4FNb7/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Shunwang Tech, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Shunwang Tech for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_bgiyuAWhRzWrIFnn1swCL5IcEpCA8FYUUwp4FNb7/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Shunwang Tech URL.
- Step 03
Save and start
Save the connection and enable Shunwang Tech in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"shunwang-tech": {
"url": "https://edge.vinkius.com/vk_preview_bgiyuAWhRzWrIFnn1swCL5IcEpCA8FYUUwp4FNb7/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Shunwang Tech
Open Agent mode in chat and ask: "Using Shunwang Tech, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"shunwang-tech": {
"url": "https://edge.vinkius.com/vk_preview_bgiyuAWhRzWrIFnn1swCL5IcEpCA8FYUUwp4FNb7/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Shunwang Tech
Ask Copilot: "Using Shunwang Tech, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"shunwang-tech": {
"url": "https://edge.vinkius.com/vk_preview_bgiyuAWhRzWrIFnn1swCL5IcEpCA8FYUUwp4FNb7/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Shunwang Tech
Open Cascade and ask: "Using Shunwang Tech, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"shunwang-tech": {
"url": "https://edge.vinkius.com/vk_preview_bgiyuAWhRzWrIFnn1swCL5IcEpCA8FYUUwp4FNb7/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Shunwang Tech
Ask Cline: "Using Shunwang Tech, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add shunwang-tech --transport http "https://edge.vinkius.com/vk_preview_bgiyuAWhRzWrIFnn1swCL5IcEpCA8FYUUwp4FNb7/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Shunwang Tech
Ask Claude: "Using Shunwang Tech, show me...". 10 tools are ready
Where the request belongs
Work Shunwang Tech can move forward.
This is for the infrastructure lead who's tired of manual node monitoring and the AI dev trying to scale inference across a distributed network.
Infrastructure Engineer
Monitors GPU clusters and sends remote commands to nodes to keep uptime high.
AI Developer
Deploys and manages inference tasks across edge networks without manual scripting.
PC Bang Manager
Oversees the health and status of large-scale gaming PC networks.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsVast.ai (GPU Rental Cloud API)
Rent high-performance GPUs for AI and deep learning. Search marketplace offers, deploy Docker containers, and manage your cloud GPU fleet.
CoreWeave (AI GPU Cloud)
Manage high-performance AI infrastructure on CoreWeave. provision GPU clusters, configure VPCs, and orchestrate inference gateways directly from your AI agent.
Guance Cloud / 观测云
Modern observability platform. manage monitors, dashboards, and events via AI.
Paperspace
Provision and track powerful GPU workloads via Paperspace. list compute instances, fetch active deployments, trace team projects, and query Gradient environments via AI.
Lambda Labs (GPU Cloud)
Manage AI infrastructure via Lambda Labs. launch GPU instances, monitor ML workloads, and manage SSH keys.
Fly.io
Manage edge infrastructure via Fly.io. monitor apps and machines, scale compute horizontally, handle persistent volumes, and run remote commands directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Shunwang Tech connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Shunwang Tech.
The practical details behind the request, access and result.
How can I use Shunwang Tech to manage my PC Bang?
You can use this Connector to let your AI agent oversee your entire PC Bang network. It can check if PCs are online, monitor their health, and send remote commands to fix issues without you needing to visit the site.
Can I use an AI agent to reboot my remote computing nodes?
Yes, the Connector allows your agent to send direct management commands like reboot or shutdown to specific nodes. This is great for clearing up hung processes or performing remote maintenance.
How do I deploy AI inference tasks on Shunwang Tech?
You can simply describe the task and the image you want to use to your AI agent. The Connector will handle the creation and deployment of that task on your designated clusters automatically.
Can Shunwang Tech help me monitor GPU usage across multiple clusters?
Absolutely. The Connector can pull resource usage summaries across your entire network, letting you see exactly how much of your GPU capacity is being used at any given moment.
Is there a way to manage edge computing nodes without a dashboard?
This Connector is designed for exactly that. It moves the management from a technical dashboard into a natural conversation with your AI client, making it much faster to get things done.
How do I get my Shunwang App Key into my AI client?
Once you subscribe via Vinkius, you'll just need to provide your Shunwang App Key and Secret in the setup. From there, your AI client can start managing your infrastructure directly.
How do I check the real-time health of a specific computing node?
Use the get_node capability with the corresponding node_id. It will return real-time metrics including CPU, GPU, and Memory usage, as well as the current online status.
Can I deploy a new computing task using the agent?
Yes. Use the create_task capability. You will need to provide the image_id and the cluster_id where you want to deploy the task. You can also optionaly give the task a name.
Is it possible to remotely reboot a node through the chat?
Yes, using the send_node_command capability. You just need the node_id and specify 'reboot' as the command. This allows for rapid remote maintenance without manual intervention.
One connection away
Give your agent a direct line to Shunwang Tech.
Connect Shunwang Tech once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available