How to Use the Tower MCP in Vercel AI SDK

Q: How can I check all projects in Tower using the Vercel AI SDK?

You call listprojects via your agent. The data streams back to your client, allowing you to render the list immediately on the frontend. You’ll see every project name appear live as it comes through.

Q: Does the Vercel AI SDK handle large lists of discussions from Tower?

Yep. If you call listdiscussions, the results stream in chunk by chunk, which is perfect for big projects. It keeps your UI snappy and responsive even if there are thousands of discussion entries.

Q: What project metadata can I access with Tower and the Vercel AI SDK?

You can stream basic project metadata like names, IDs, and status using tools like getproject. This is all visible to your agent client when running through the MCP Server.

Q: When updating a task in Tower with Vercel AI SDK, what happens?

You call updatetask, and because the result streams, you can give immediate user feedback. The UI shows the update confirmation populating right where the original task card was.

Q: How does data privacy work when using Tower with Vercel AI SDK?

The server touches user records and project metadata. Your agent client handles all authentication, ensuring that your user's tokens are used to access the required information from the MCP Server.

See project details and task updates stream live in your UI 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 Tower MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Project Data Streaming

When you call `list_projects`, you get the results to appear right away. You don't have to wait for a loading spinner; the data streams straight into your React or Next.js component. This makes building user-facing products simple. Your agent calls the MCP Server, and the user sees the project list populate live as the response arrives.

Monitoring Team Member Changes

Need to show team member counts in real time? Use `list_members` to get current roster data. The result streams directly into your UI, allowing you to update components without extra API calls. This is huge for dashboards. You can build a live directory that updates instantly when the agent retrieves data from the Tower MCP Server.

Getting Current Task Status

You can fetch specific details using `get_task_details`. This operation streams back exactly what you need—the status, assignee, and description. It's immediate, granular data. This eliminates the 'wait-and-reload' pattern. If your user clicks a task link, they see the full context populating instantly.

Setup guide

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

You call `list_projects` via your agent. The data streams back to your client, allowing you to render the list immediately on the frontend. You’ll see every project name appear live as it comes through.

Yep. If you call `list_discussions`, the results stream in chunk by chunk, which is perfect for big projects. It keeps your UI snappy and responsive even if there are thousands of discussion entries.

You can stream basic `project metadata` like names, IDs, and status using tools like `get_project`. This is all visible to your agent client when running through the MCP Server.

You call `update_task`, and because the result streams, you can give immediate user feedback. The UI shows the update confirmation populating right where the original task card was.

The server touches `user records` and `project metadata`. Your agent client handles all authentication, ensuring that your user's tokens are used to access the required information from the MCP Server.

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