JD Cloud Infrastructure MCP. Control your entire JD Cloud environment from your AI agent.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
JD Cloud Infrastructure MCP Server. Control your entire JD Cloud environment from your AI client. Use this to manage VMs, disks, databases, and network IPs without switching dashboards.
List, start, stop, and reboot compute instances. Pull time-series CPU metrics. Inspect storage buckets and RDS databases. It's your single pane of glass for JD Cloud ops.
What your AI agents can do
Describe cloud disk
Retrieves detailed information about one specific cloud disk volume.
Describe metric data
Pulls time-series monitoring data (CPU, network, disk) for a specified cloud resource.
Describe vm instance
Gets detailed operational information about a specific virtual machine instance.
Start, stop, reboot, or retrieve detailed information about any VM instance.
List all cloud disks and inspect Object Storage Service buckets.
Pull time-series metrics (CPU, network, disk) for any specific cloud resource.
List and check the status of all allocated Elastic IP addresses.
List all RDS database instances, including engine versions and connection status.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
JD Cloud Infrastructure: 11 Tools for Cloud Ops
These tools let your AI agent manage every aspect of your JD Cloud environment, from listing resources to changing VM states and pulling performance metrics.
019d844adescribe cloud disk
Retrieves detailed information about one specific cloud disk volume.
019d844adescribe metric data
Pulls time-series monitoring data (CPU, network, disk) for a specified cloud resource.
019d844adescribe vm instance
Gets detailed operational information about a specific virtual machine instance.
019d844alist cloud disks
Lists every cloud disk volume in your designated region.
019d844alist elastic ips
Lists all Elastic IP addresses allocated in your region.
019d844alist oss buckets
Lists all Object Storage Service buckets in your region.
019d844alist rds instances
Lists all RDS database instances within your region.
019d844alist vm instances
Lists all virtual machine instances in your JD Cloud region.
019d844areboot vm instance
Reboots a specified VM instance immediately.
019d844astart vm instance
Starts a VM instance that is currently stopped.
019d844astop vm instance
Stops a running VM instance.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with JD Cloud Infrastructure, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're gonna control your whole JD Cloud setup straight from your AI client. This MCP gives your agent direct access to manage VMs, disks, databases, and network IPs without you having to jump between dashboards. You'll list, start, stop, and reboot compute instances. You can also pull time-series CPU metrics.
You'll inspect storage buckets and RDS databases. It's your single pane of glass for JD Cloud ops.
Managing Virtual Machines: Use list_vm_instances to see all the VMs in your JD Cloud region. You can then check specific instances with describe_vm_instance. You've got the power to start a stopped VM with start_vm_instance, stop a running one using stop_vm_instance, or reboot it immediately with reboot_vm_instance.
Storage and Disks: You can see every cloud disk volume in your region by running list_cloud_disks. For details on one specific disk, use describe_cloud_disk. You can list all your Object Storage Service buckets with list_oss_buckets.
Networking: To check network connectivity, run list_elastic_ips to list all allocated Elastic IP addresses.
Monitoring Performance: You pull time-series monitoring data—CPU, network, and disk metrics—for any resource using describe_metric_data.
Databases: You can list all RDS database instances in your region using list_rds_instances. This tool tells you the engine versions and connection status for each one.
How JD Cloud Infrastructure MCP Works
- 1 Generate IAM Access Keys in the JD Cloud Console.
- 2 Input your Access Key, Secret Key, and Region ID into Vurb.
- 3 The MCP engine uses these credentials to construct the
JDCLOUD2-HMAC-SHA256signature for every API call your AI agent makes.
The bottom line is, you give your AI client the keys and the region, and it handles the secure signing and calling of the JD Cloud APIs.
Who Is JD Cloud Infrastructure MCP For?
The DevOps engineer who gets tired of clicking through ten different dashboards at 2 a.m. The SRE team member who needs to check real-time CPU metrics and restart a failing instance without leaving their IDE. Supply Chain Architects who oversee the cloud backbone powering massive logistics networks.
Manages the cloud infrastructure by issuing commands like start_vm_instance or list_cloud_disks directly through conversational AI, eliminating dashboard switching.
Queries real-time metrics using describe_metric_data and automatically restarts unhealthy instances via reboot_vm_instance through an automated agent.
Oversees the full resource stack—from list_rds_instances to list_elastic_ips—to ensure the entire cloud backbone is correctly provisioned.
What Changes When You Connect
- Manage the full compute lifecycle (start, stop, reboot) using tools like
start_vm_instanceandstop_vm_instance. You don't have to switch to the VM dashboard to change state. - Get deep insights into resource health. Use
describe_metric_datato pull CPU, network, and disk metrics for any resource, letting you verify if an instance is actually healthy. - See all your storage assets in one go.
list_cloud_disksandlist_oss_bucketslet you see every disk and bucket without clicking through a resource inventory. - Streamline database checks.
list_rds_instancesgives you a quick overview of every RDS instance, showing the engine version and current connection status. - Handle networking without logging in.
list_elastic_ipslets you see every allocated IP address and its association status, even if it's not attached to a running VM. - Inspect any resource's details instantly.
describe_vm_instanceanddescribe_cloud_diskpull all the specific details you need without guesswork.
Real-World Use Cases
The Instance is Slow, But I Don't Know Why.
A developer notices a service is lagging. Instead of manually checking the instance console, they ask their agent to describe_metric_data for the VM ID. The agent pulls the CPU usage, shows a peak of 90% over the last hour, and suggests a capacity increase. Problem solved in seconds.
I Need to Scale Up the Backend, But I Don't Know Which IPs are Free.
A DevOps engineer needs to provision a new service but can't find an available IP. They ask the agent to list_elastic_ips. The agent returns the full list, highlighting the free or unassociated addresses, allowing the engineer to proceed immediately.
The Database Seems Stuck After an Update.
An SRE team member suspects an RDS issue. They use list_rds_instances to verify the status, then ask the agent to describe_vm_instance for the associated compute layer. They confirm the compute layer is running, but the database status suggests a connection issue, narrowing the fix.
I Need to Clean Up Old, Unattached Storage.
A cloud architect reviews resources. They run list_cloud_disks to see all disks, then cross-reference the list with running VMs using describe_vm_instance. They identify and flag disks that are detached and consuming unnecessary resources.
The Tradeoffs
Manually checking every resource type
Opening the VM console, then clicking over to the Disk console, then checking the RDS dashboard, and finally running a separate check for Elastic IPs. This takes 15 minutes and involves copy-pasting IDs.
→
Ask your agent to run list_vm_instances and list_cloud_disks together. Then, follow up with list_rds_instances and list_elastic_ips. You get all resource states and IDs in a single, automated query.
Guessing the correct VM state change tool
Trying to use a generic 'change state' command, which fails because the system requires specific actions. The user wastes time figuring out if they need to 'stop' or 'pause' the machine.
→
Use the specific tools: stop_vm_instance to halt the machine cleanly, or start_vm_instance to bring it back online. For a hard reset, use reboot_vm_instance.
Ignoring resource metrics
Just restarting a VM because it's slow, without checking the root cause. This is often a temporary fix that masks the underlying capacity issue.
→
First, run describe_metric_data to pull CPU utilization and network throughput. If metrics show sustained high load, you need to scale up, not just reboot.
When It Fits, When It Doesn't
Use this MCP if your primary goal is comprehensive visibility and automated state management across multiple JD Cloud services. It's perfect for SREs and DevOps engineers who need to diagnose an issue by pulling metrics (describe_metric_data) and then fixing it by changing state (stop_vm_instance, start_vm_instance)—all without leaving their terminal. Don't use this if you just need to build a single API wrapper for one resource type, or if you only need basic read access (a dedicated read-only tool might suffice). If your workflow is complex and requires coordinating multiple resource types (e.g., 'list disks, then check metrics, then reboot the VM'), this is the right choice.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by JD Cloud. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 11 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Checking cloud infrastructure status shouldn't require logging into five different dashboards.
Today, checking a single service's health is a pain. You have to jump to the VM console to see if the instance is running. Then, you open the Storage console to check if the attached disk is accessible. Next, you have to check the RDS dashboard to make sure the database is online. If you're doing this for a critical incident, you're spending time clicking and copy-pasting IDs instead of fixing the problem.
With this MCP, you ask your agent to check the full stack. It runs `list_vm_instances`, `describe_cloud_disk`, and `list_rds_instances` in sequence, compiling a single report. You get the status of every key component instantly.
JD Cloud Infrastructure MCP Server: Start, Stop, and Reboot VMs
Before, changing a VM's state was a multi-step process: finding the ID, navigating to the console, selecting the 'stop' button, waiting for the state change, and then repeating the process for starting it back up. This was tedious, especially during an incident.
Now, you tell your agent to 'Stop the staging environment VM.' It executes `stop_vm_instance` and waits for confirmation. When you're done, you simply say 'Start it,' and it runs `start_vm_instance`. The workflow is direct and reliable.
Common Questions About JD Cloud Infrastructure MCP
How do I check the current CPU usage using describe_metric_data? +
You must provide the specific resource ID (e.g., i-abc123) and the metric name (e.g., cpu.util). The agent pulls time-series data, giving you average and peak usage percentages over a specified time window.
Which tool do I use to list all my cloud disks? +
Use list_cloud_disks. This tool pulls a complete list of every cloud disk volume in your JD Cloud region, regardless of whether it's currently attached to a VM.
Can I list all my running VMs and their status? +
Yes, use list_vm_instances. It returns a comprehensive list of all virtual machine instances, showing their current status (running, stopped, etc.).
What is the difference between reboot_vm_instance and start_vm_instance? +
Use start_vm_instance when the machine is fully stopped and you need to power it on. Use reboot_vm_instance when the machine is already running but needs a clean restart of its operating system.
How do I check the connection status of my RDS database? +
Run list_rds_instances. This tool lists all your RDS database instances and includes their current connection status and engine version for quick auditing.
How do I list all my Object Storage Service buckets using list_oss_buckets? +
You use list_oss_buckets to get a full inventory of all your Object Storage buckets. This is useful for quickly seeing which buckets exist before you need to inspect or manage their contents.
What does describe_vm_instance provide about a specific VM, and how do I use it? +
The describe_vm_instance tool gives you comprehensive details on a VM, including its ID, allocated vCPUs, and general status. You provide the VM ID when calling this tool.
Can I query Elastic IP allocations and their status using list_elastic_ips? +
Yes, list_elastic_ips fetches a list of all Elastic IP addresses associated with your account in the region. It shows the allocation status and associated resources for each IP.
Is the JDCLOUD2-HMAC-SHA256 signing handled automatically? +
Yes. The MCP engine locally derives signing keys through HMAC chains (date → region → service → jdcloud2_request), constructs canonical requests, and injects the Authorization header transparently. Your AI never handles raw crypto.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Amazon DynamoDB Table
This MCP does exactly one thing: it manages items in a single Amazon DynamoDB Table. That's its only function, and nothing else. Incredible for giving your AI a secure NoSQL database.
Dropbox Sign
Get documents signed electronically with legally binding e-signatures, templates, and audit trails your business can trust.
Starburst
Connect your AI to Starburst Enterprise. Query federated data lakes, manage access roles, and orchestrate complex data environments seamlessly.
You might also like
Glofox
Manage members, classes, trainers, bookings, and purchases for your Glofox-powered gym or fitness studio through natural conversation.
Aporia
Monitor AI models and validate LLM interactions with guardrails directly from your AI agent to ensure safety and observability.
Illumidesk
Manage campuses, courses, and users via Illumidesk LMS API.