How to Use the Baidu Analytics / 百度统计 MCP in Vercel AI SDK

Q: How do I stream Baidu Analytics / 百度统计 data with Vercel AI SDK?

Install @ai-sdk/mcp and configure the MCP client to talk to our endpoint URL. You then pass the tools from the client directly into streamText to let your LLM query Chinese traffic metrics on demand.

Q: What custom metrics can I query through this integration?

You can execute complex, targeted queries using querycustommetrics. This allows your chat interface to pull specific dimensions like search engine referrers or custom event tracking that default tools skip.

Feed live Chinese web traffic data directly into your Vercel AI SDK frontend without making users wait on a loading spinner.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baidu Analytics / 百度统计 MCP to Vercel AI SDK

Create your Vinkius account to connect Baidu Analytics / 百度统计 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 Baidu Analytics / 百度统计 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed live Chinese traffic to your Vercel AI SDK setup

Your React or Next.js frontend can now display live traffic metrics from China as they happen. By hooking this MCP server into your streaming setup, the client fetches real-time visitor numbers via `get_realtime_metrics` and renders them instantly. Users see the numbers roll in line-by-line rather than staring at a blank card. We built this to bypass the slow load times of foreign APIs behind the Great Firewall. Your interface stays fast because the SDK handles the stream while the `list_sites` tool finds the right tracking ID.

Map geographic visitor distribution with our MCP Server

Pinpoint exactly where your Chinese users live without leaving your chat interface. Your frontend agent calls `get_geo_distribution` to pull province-level data and maps it right inside the streaming component. This gives your team immediate clarity on Chinese regional performance during product launches. You don't need to build custom dashboard widgets or write complex polling logic to see your Baidu metrics. The Vercel AI SDK receives raw JSON from the server and maps it to your custom React map component on the edge.

Analyze content performance with instant rank tables

Let your users ask which blog posts are trending in Beijing and get an immediate, sorted table back. The agent invokes `get_page_rankings` alongside `get_yesterday_overview` to compare page views and bounce rates from the previous day. It formats this data cleanly inside the active chat window. This eliminates the need to log into the Chinese analytics console just to check yesterday's top articles. The SDK streams the markdown table directly, letting your content team audit their reach in seconds.

Setup guide

Set up Baidu Analytics / 百度统计 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 Baidu Analytics / 百度统计 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 Baidu Analytics / 百度统计 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 Baidu Analytics / 百度统计. 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 Baidu Analytics / 百度统计 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 Baidu Analytics / 百度统计 MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and configure the MCP client to talk to our endpoint URL. You then pass the tools from the client directly into `streamText` to let your LLM query Chinese traffic metrics on demand.

Yes, it easily manages multiple properties. The agent calls `list_sites` first to find the correct site ID, then feeds that ID into `get_daily_trend` or other tools to pull the right dataset.

Not at all, because our managed MCP server handles the connection outside your edge runtime. Your edge functions simply call our endpoint, keeping your Vercel execution times well under the standard limits.

You can execute complex, targeted queries using `query_custom_metrics`. This allows your chat interface to pull specific dimensions like search engine referrers or custom event tracking that default tools skip.

We isolate your credentials inside a secure, ephemeral V8 sandbox that never persists your tokens. When your Vercel AI SDK client requests visitor IP geolocations or page views, the server processes the request in transit and wipes the memory immediately after the session closes.

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