How to Use the Height (Project Management) MCP in Vercel AI SDK

Q: How do I pass Height (Project Management) tools to the Vercel AI SDK?

Initialize the connection to the MCP Server using createMCPClient with your HTTP endpoint. Then, pass the output of mcpClient.tools() directly into the tools parameter of generateText or streamText to let your agent query tasks.

Feed Height (Project Management) task lists and workspace activities straight into Vercel AI SDK UI components without 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 Height (Project Management) MCP to Vercel AI SDK

Create your Vinkius account to connect Height (Project Management) 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 Height (Project Management) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream real-time task views in Vercel AI SDK

Your AI client uses `list_tasks` to fetch active ticket states without freezing your UI. When your agent calls the tool through this MCP Server, the raw task data streams directly into your React or Next.js components as it arrives. Your users see active tickets load line-by-line instead of staring at a blank loading screen. This direct streaming works by passing the server's tools array into your SDK text generation functions. If a user asks what's on their plate, the model invokes `get_task` to pull the exact ticket payload and displays it instantly on the edge.

Trace team activities inside your frontend

Tracking chronological updates across your team becomes simple when your agent calls `list_activities` directly from your workspace. This integration exposes the activity log so your Vercel AI SDK setup can pull recent updates and changes directly into your custom dashboard. The agent parses the raw activity stream and populates your UI with clean chronological updates. You don't have to write custom polling logic or sync engines. Just let your agent query the `workspace` endpoint through this MCP setup to map out the entire team's active workflow in a single, lightweight call.

Map lists and assignees on the edge

Your client uses `list_lists` to find active project boards and maps them against team members to see who is carrying the heaviest load. Route tasks and check workloads without heavy backend middleware by letting your agent query these endpoints on demand. Because this setup runs fine in Edge Functions, you can run these lookups instantly. The SDK handles the connection, fetches the list structures via `list_users`, and displays current sprint ownership before your user can even think about refreshing.

Setup guide

Set up Height (Project Management) 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 Height (Project Management) 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 Height (Project Management) 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 Height. 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 Height (Project Management) 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 Height (Project Management) MCP in Vercel AI SDK

Initialize the connection to the MCP Server using `createMCPClient` with your HTTP endpoint. Then, pass the output of `mcpClient.tools()` directly into the `tools` parameter of `generateText` or `streamText` to let your agent query tasks.

No, this specific server is read-only. It provides tools like `get_task` and `list_tasks` for auditing and reporting, meaning your agent can display and analyze project data but cannot create or change tickets.

This MCP Server runs as a hosted V8 isolate on Vinkius, meaning your edge function only makes a quick HTTP call to fetch task data. It keeps your edge bundle small and prevents timeout issues during large `list_activities` queries.

No, Vinkius handles the authorization layer. Your application connects using a single secure endpoint token, and the platform manages the underlying credentials to fetch lists and users safely.

Your task descriptions, activity logs, and list structures never persist on our servers. Every request to `workspace` or `get_task` runs through our secure MCP gateway in an ephemeral, zero-trust sandbox that is destroyed immediately after your agent receives the payload.

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