How to Use the Basecamp MCP in Vercel AI SDK

Q: How do I stream Basecamp task updates with the Vercel AI SDK?

Call mcpClient.tools() and pass them to streamText. When the user asks to see tasks, the model calls listtodos and streams the JSON array directly to your UI components.

Q: How do I handle Basecamp user authentication in a Vercel AI SDK app?

Use the authProvider configuration during the createMCPClient setup. This securely routes the user's OAuth token to the Vinkius managed endpoint, granting access to getmyprofile without exposing secrets to the client.

Q: What happens if a tool call fails during a stream?

The Vercel AI SDK catches the error from tools like updatetodo and surfaces the raw error message in the tool invocation result. Your UI can catch this state to show a local error boundary.

Build Next.js apps where Basecamp tasks and messages stream into your UI in real-time 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 Basecamp MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Basecamp Todo Feeds via Vercel AI SDK

The `list_todos` tool pulls pending tasks directly from your project dock into your application's active viewport. Your frontend renders these items as they load, avoiding the usual blank loading states that ruin the user experience. When users check off tasks, the `complete_todo` tool updates the status instantly in Basecamp. The UI reflects this state change immediately without waiting for a full page refresh, keeping the interface snappy.

Real-time Commenting via MCP Server

The `create_comment` tool pushes rich text HTML updates directly to any active Basecamp recording ID. Your AI client drafts and posts responses while streaming the raw text straight to the user's screen. If someone posts a bad update, your interface uses `get_message` to pull down the full thread details. This allows the Vercel AI SDK to feed the context back into the LLM context window for instant correction.

Dynamic Project Creation and Setup

The `create_project` tool builds a new workspace from scratch with default tools like message boards and to-do sets enabled. This MCP Server exposes the newly minted project ID and dock tool IDs directly to your edge function. Right after creation, the `update_project` tool modifies the name or description based on user input. The React frontend displays these changes as the LLM executes the calls, giving users a live view of their project setup.

Setup guide

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

Call `mcpClient.tools()` and pass them to `streamText`. When the user asks to see tasks, the model calls `list_todos` and streams the JSON array directly to your UI components.

Yes. This MCP Server works in Edge Functions because it communicates over a lightweight HTTP transport. You initialize the client, call `create_project`, and close the connection immediately.

Use the `authProvider` configuration during the `createMCPClient` setup. This securely routes the user's OAuth token to the Vinkius managed endpoint, granting access to `get_my_profile` without exposing secrets to the client.

The Vercel AI SDK catches the error from tools like `update_todo` and surfaces the raw error message in the tool invocation result. Your UI can catch this state to show a local error boundary.

Your Basecamp to-do lists, messages, and comments remain protected inside an isolated V8 sandbox. Vinkius handles the authorization token securely and never stores the content of your project discussions or tasks on its servers.

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