How to Use the AdaptiveWork (Clarizen) MCP in Vercel AI SDK

Q: How do I connect AdaptiveWork (Clarizen) to the Vercel AI SDK?

Install @ai-sdk/mcp and instantiate createMCPClient using your Vinkius HTTP transport URL. Then pass the resulting tools into your generateText or streamText calls. Always remember to call mcpClient.close() when the session ends.

Q: Can the Vercel AI SDK stream AdaptiveWork (Clarizen) task updates?

Yes. When your agent calls listtasks, the raw JSON response streams back through the Vercel provider. Your Next.js frontend renders those line items progressively.

Q: Does Vercel AI SDK support OAuth for AdaptiveWork (Clarizen) tools?

It does. You configure the authProvider in your MCP Server setup to handle Clarizen credentials. Vinkius manages the actual token exchange so your edge functions stay clean.

Stream live AdaptiveWork (Clarizen) project metrics directly into your React frontends 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 AdaptiveWork (Clarizen) MCP to Vercel AI SDK

Create your Vinkius account to connect AdaptiveWork (Clarizen) 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 AdaptiveWork (Clarizen) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream AdaptiveWork (Clarizen) MCP Server Data Live

Building a custom PM dashboard in Next.js means you need data fast. You connect your Vercel AI SDK setup to this endpoint, and suddenly your users watch project statuses load instantly. They ask for an update, and the system pulls active lists using `list_projects` without making them stare at a loading spinner. The real magic happens when you combine tools. Your edge function hits `get_project_details` and streams the progress metrics right into your React components. End users see the exact percentage complete tick up in real-time as the agent gathers the information.

Build Interactive Task Creation UIs

Nobody wants to wait for a form submission to clear. When a user types a request to spin up a new deliverable, your agent intercepts it and fires off `create_task`. It grabs the parent ID automatically from context. Because Vercel handles the streaming response, the new task appears in your Svelte or Vue interface instantly. You just pass `mcpClient.tools()` to `streamText`, and the heavy lifting happens behind the scenes.

Execute Raw CZQL from the Edge

Sometimes standard API endpoints fall short for complex reporting. That is why we exposed `run_query` so your TypeScript code can pass raw Clarizen Query Language directly to the system. Your AI client writes the CZQL syntax on the fly based on what the user asked for. It grabs the exact resource assignments via `list_users` and joins that context, streaming a highly specific progress report back to the frontend before a traditional backend could even boot up.

Setup guide

Set up AdaptiveWork (Clarizen) 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 AdaptiveWork (Clarizen) 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 AdaptiveWork (Clarizen) 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 AdaptiveWork. 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 AdaptiveWork (Clarizen) 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 AdaptiveWork (Clarizen) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and instantiate `createMCPClient` using your Vinkius HTTP transport URL. Then pass the resulting tools into your `generateText` or `streamText` calls. Always remember to call `mcpClient.close()` when the session ends.

Yes. When your agent calls `list_tasks`, the raw JSON response streams back through the Vercel provider. Your Next.js frontend renders those line items progressively.

It does. You configure the `authProvider` in your MCP Server setup to handle Clarizen credentials. Vinkius manages the actual token exchange so your edge functions stay clean.

Standard APIs require you to build endpoints, write fetch logic, and handle loading states. This MCP endpoint gives your agent direct, type-safe access to project data, skipping the middleware entirely.

Your active project lists and custom CZQL query results stay completely isolated. Vinkius runs every request inside a V8 Isolate Sandbox that spins down the second the operation finishes. Nothing persists in memory.

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