How to Use the JD Cloud / 京东云 MCP in Vercel AI SDK

Q: How do I connect JD Cloud / 京东云 to Vercel AI SDK?

Install @ai-sdk/mcp and ai. Create an MCP client pointing to your Vinkius endpoint, then pass the tools from mcpClient.tools() into streamText or generateText. Remember to call mcpClient.close() when the session ends to prevent memory leaks.

Q: Is my JD Cloud / 京东云 billing and VM metadata secure when using Vercel AI SDK?

Yes, completely secure. All data retrieved via getbillingsummary and getvmdetail is encrypted in transit using TLS 1.3. Vinkius executes the server in an ephemeral sandbox, meaning your raw infrastructure configurations and cost metrics are never stored or logged on the host platform.

Render live JD Cloud infrastructure states directly in your Next.js components with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JD Cloud / 京东云 MCP to Vercel AI SDK

Create your Vinkius account to connect JD Cloud / 京东云 to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup JD Cloud / 京东云 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time VM Inspection for Next.js

Your users don't want to wait for a full page reload to check if their JD Cloud compute instances are online. Pass `list_vm_instances` directly to `streamText` and watch the virtual machine list render line-by-line in your React components. When a user clicks a specific VM, your Next.js app uses `get_vm_detail` to pull JD Cloud CPU allocations on the fly. Because this runs on Vercel Edge Functions, the infrastructure metadata returns instantly without cold starts.

Live Storage Audits via Vercel AI SDK

Keeping track of JD Cloud storage costs means watching your object storage closely. The Vercel AI SDK calls `list_oss_buckets` to pull your bucket inventory and feeds it directly into your UI. From there, your frontend agent can trigger `list_cloud_disks` to find unattached block storage volumes that are burning your budget. You get a live, interactive list on your screen without writing custom API fetching logic.

Instant Infrastructure Budget Checks

Developers can query JD Cloud billing data using a simple Next.js chat interface. This MCP Server exposes `get_billing_summary` directly to your AI client, letting users ask about cost spikes. You can combine this with `get_account_profile` to verify which IAM user ran up the bill. The billing data streams straight to your dashboard, making cloud cost tracking transparent.

Setup guide

Set up JD Cloud / 京东云 MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all JD Cloud / 京东云 tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent JD Cloud / 京东云 transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

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 / 京东云. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect JD Cloud / 京东云 now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about JD Cloud / 京东云 MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and `ai`. Create an MCP client pointing to your Vinkius endpoint, then pass the tools from `mcpClient.tools()` into `streamText` or `generateText`. Remember to call `mcpClient.close()` when the session ends to prevent memory leaks.

Yes, the Vercel AI SDK is designed for edge runtimes. The HTTP transport option in the MCP client connects to your hosted server on Vinkius without requiring heavy local dependencies. This keeps your Edge Function startup times under the limit.

The SDK executes tool calls sequentially when streaming responses. If your agent runs `list_cicd_pipelines` or `list_vpc_networks` repeatedly, you should implement caching or rate-limiting wrappers around the tool execution block to avoid hitting JD Cloud API thresholds.

Vinkius manages the raw JD Cloud API keys securely. Your Vercel AI SDK application only needs to provide the single Vinkius endpoint token in the headers of your HTTP transport setup, keeping your cloud credentials out of your frontend code.

Yes, completely secure. All data retrieved via `get_billing_summary` and `get_vm_detail` is encrypted in transit using TLS 1.3. Vinkius executes the server in an ephemeral sandbox, meaning your raw infrastructure configurations and cost metrics are never stored or logged on the host platform.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript