How to Use the DeveloperHub MCP in Vercel AI SDK

Q: How do I stream search results from DeveloperHub using the Vercel AI SDK?

You pass the searchdocumentationportal tool to the streamText function. The Vercel AI SDK will automatically handle calling the tool and streaming the markdown from getdocumentationpagecontent back into your UI components.

Q: Can I build a component that only shows recent DeveloperHub changes with the Vercel AI SDK?

Yes. Your agent can periodically call listrecentlyupdatedpages or listproductchangelogs. The AI SDK's streaming capabilities let you render those updates live in a dedicated component without any page reloads.

Q: How can the Vercel AI SDK help me compare two DeveloperHub documentation versions?

Your agent can call listdocumentationversions to get the available versions. Then, it can use listdocumentationpages on both versions, diff the results, and stream a summary of the changes into your UI.

Stream DeveloperHub docs and changelogs directly into your app's UI with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeveloperHub MCP to Vercel AI SDK

Create your Vinkius account to connect DeveloperHub 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 DeveloperHub with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Live-Updating Doc Viewer

Stop forcing users to refresh the page for documentation updates. Your agent can use `list_recently_updated_pages` to spot changes and then stream the new content directly into your React components with `get_documentation_page_content`. You can build a real-time 'What's New' feed by watching `list_product_changelogs`. The Vercel AI SDK renders the data as it arrives, so your users see the latest API changes appearing in the UI character by character. It's a much better experience than a static page.

Create a Custom Search Front-End

The built-in search on your doc portal might not be what you want. This DeveloperHub MCP Server lets you build your own. Feed a user's query into your agent, which calls `search_documentation_portal` and streams the results back. Combine that with `get_documentation_sitemap` to create a dynamic navigation tree that reflects your project's exact structure. You get full control over the search UI and how results are displayed in your Next.js or Svelte application, all powered by your agent.

Give Users Account-Aware Context

Personalize the documentation experience. When a user is logged in, your agent can call `get_account_metadata` to check their specific usage limits or account type. This isn't just generic content anymore. With that context, your UI can show relevant warnings, highlight specific features available to their plan, or even use `list_documentation_projects` to only show the projects they actually have access to. It makes the docs feel like part of your application, not a separate website.

Setup guide

Set up DeveloperHub 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 DeveloperHub 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 DeveloperHub 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 DeveloperHub. 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 DeveloperHub 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 DeveloperHub MCP in Vercel AI SDK

You pass the `search_documentation_portal` tool to the `streamText` function. The Vercel AI SDK will automatically handle calling the tool and streaming the markdown from `get_documentation_page_content` back into your UI components.

Yes. Your agent can periodically call `list_recently_updated_pages` or `list_product_changelogs`. The AI SDK's streaming capabilities let you render those updates live in a dedicated component without any page reloads.

Absolutely. The Vercel AI SDK and the MCP transport are fully compatible with the Edge runtime. You can run your agent functions close to your users for lower latency when fetching doc content.

Your agent can call `list_documentation_versions` to get the available versions. Then, it can use `list_documentation_pages` on both versions, diff the results, and stream a summary of the changes into your UI.

It only accesses your documentation content, project metadata, changelogs, and account usage limits. All requests are made over HTTPS to the Vinkius-managed MCP server, which processes each tool call in an ephemeral, sandboxed environment. Your DeveloperHub key is encrypted at rest.

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