How to Use the Archbee MCP in Vercel AI SDK

Q: How do I stream Archbee documentation updates using the Vercel AI SDK?

Call mcpClient.tools() to grab the schema and pass them to streamText. The SDK streams the output of tools like createupdatedoc directly to your React components as the AI client writes.

Q: Do I need to manually close the connection after querying Archbee?

Always call mcpClient.close() once your stream completes. Leaving connections open leaks memory on serverless platforms, which slows down subsequent calls to tools like searchdocs.

Build live-updating developer portals where your Vercel AI SDK frontend streams real-time technical docs directly from Archbee.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Archbee MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Update API references live with Vercel AI SDK

The `sync_openapi` tool pushes raw OpenAPI specifications directly to your documentation spaces without leaving your terminal. Your frontend application calls this tool inside your Next.js API routes, letting your AI client instantly process schema changes and display updated endpoints. Because the Vercel AI SDK streams responses, developers see the exact sync progress of `info_openapi` as it happens. You avoid long loading spinners and page freezes while rebuilding complex technical API references.

Search and render docs instantly in your UI

The `search_docs` tool queries your entire knowledge base to find specific articles or API keys. Your custom interface renders these results on the fly, feeding the raw content from `get_doc` directly into your UI components. Build interactive search bars where users ask questions and watch the AI client fetch and format the text in real-time. This setup bypasses slow server-side page reloads by using Edge-compatible streams with this MCP Server to deliver raw markdown data.

Draft and publish changes on the Edge

The `create_update_doc` tool edits and writes technical guides directly from the user's chat input. The AI client handles the heavy lifting of updating layout structures, then triggers `publish_space` to push the changes to production. This MCP Server integration runs inside Edge Functions, keeping your bundle sizes small and your response times low. Users modify documentation layouts and write new technical drafts with zero latency.

Setup guide

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

Call `mcpClient.tools()` to grab the schema and pass them to `streamText`. The SDK streams the output of tools like `create_update_doc` directly to your React components as the AI client writes.

Yes, the client setup is lightweight and works within Edge runtimes. Use `createMCPClient` with an HTTP transport to execute tools like `get_doc` without cold-start delays.

The SDK relies on your backend execution logic to catch rate limit errors. Wrap your `sync_openapi` calls in standard try-catch blocks to handle API throttling before streaming the response to the user.

Always call `mcpClient.close()` once your stream completes. Leaving connections open leaks memory on serverless platforms, which slows down subsequent calls to tools like `search_docs`.

Your actual markdown files and API schemas never pass through third-party servers. The MCP Server acts as a secure bridge, passing credentials directly to the API endpoint and keeping your sensitive internal guides isolated.

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