How to Use the Ayanza MCP in Vercel AI SDK

Q: How do I install the Ayanza MCP Server for Vercel AI SDK?

Run npm install ai @ai-sdk/mcp to get started. You then configure the transport to point to your Vinkius endpoint URL and pass the tools directly into your SDK call.

Q: Can I stream live Ayanza task updates using Vercel AI SDK?

Yes, that is the main reason to use this setup. By feeding listtasks into streamText, your UI updates dynamically as the model fetches and formats the task data.

Q: How does Vercel AI SDK handle authentication with Ayanza?

You use the SDK's authProvider to pass user-specific tokens. This keeps actions like createtask tied to the correct user instead of a single master key.

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

Yes, always call mcpClient.close() at the end of your execution block. This prevents connection leaks, especially when running inside short-lived Vercel serverless or edge environments.

Stream Ayanza task updates and wiki changes directly into your React UI using 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 Ayanza MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time task streaming with Vercel AI SDK

When your React app calls `list_tasks` or `create_task`, this MCP Server pipes the raw Ayanza data straight into your UI thread. You get instant rendering of task lists and assignments without the typical lag of traditional API polling. Setting this up takes seconds. You pull the tools via `mcpClient.tools()` and drop them right into `streamText` so your AI model can edit tasks using `update_task` and show the changes live.

Direct wiki and workspace lookups on the edge

This MCP Server lets you run Ayanza integrations on Vercel Edge Functions using `list_wiki_pages` or `list_users` to scan your workspace with zero cold starts. Your agent can query team documentation or find user profiles instantly on a zero-latency runtime. The Vercel AI SDK handles the connection state cleanly. You just initialize the client, run your workspace queries, and always call `mcpClient.close()` to keep your edge executions fast.

Secure user-scoped task management

This MCP setup runs secure, user-scoped task management by using `get_me` to verify who is actually making changes. Use the `authProvider` config in your Vercel AI SDK setup to pass user-specific tokens rather than hardcoding master keys. Your workspace remains safe because actions map directly to that user's permissions when calling `delete_task` or `get_project`.

Setup guide

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

Run `npm install ai @ai-sdk/mcp` to get started. You then configure the transport to point to your Vinkius endpoint URL and pass the tools directly into your SDK call.

Yes, that is the main reason to use this setup. By feeding `list_tasks` into `streamText`, your UI updates dynamically as the model fetches and formats the task data.

You use the SDK's `authProvider` to pass user-specific tokens. This keeps actions like `create_task` tied to the correct user instead of a single master key.

Yes, always call `mcpClient.close()` at the end of your execution block. This prevents connection leaks, especially when running inside short-lived Vercel serverless or edge environments.

Your task descriptions, project names, and wiki text never persist on Vinkius. Every call to `get_project` or `list_wiki_pages` runs inside an isolated, ephemeral sandbox that wipes itself clean immediately after execution.

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