How to Use the AdaptiveWork (Clarizen) MCP in Mastra AI

Q: How do I configure AdaptiveWork (Clarizen) tools in Mastra AI?

Initialize a new MCPClient and pass your Vinkius URL into the servers object. Mastra auto-detects the streamable HTTP transport. From there, just spread the exposed tools into your agent's definition.

Q: Can Mastra AI require human approval for AdaptiveWork (Clarizen) tasks?

You certainly can. You can set requireToolApproval on destructive actions like createtask. The workflow pauses, waits for a human to review the parent ID and task name, and only proceeds once approved.

Build resilient, multi-step project management workflows in Mastra AI that handle AdaptiveWork API failures gracefully.

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 Mastra AI

Create your Vinkius account to connect AdaptiveWork (Clarizen) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Resilient AdaptiveWork (Clarizen) Workflows

Project management APIs fail. Rate limits hit, tokens expire, and networks drop. When you connect Mastra AI to this MCP endpoint, you get automatic retries with exponential backoff right out of the box. If a call to `list_projects` times out, your workflow does not crash. Mastra waits, tries again, and keeps moving. You build complex syncs between Clarizen and your other systems knowing the underlying engine handles the bumps.

Chain Clarizen Tools with Conditional Logic

Basic scripts just run top to bottom. Mastra lets you build actual logic trees where the outcome of `get_project_details` determines the next step. If a project is behind schedule, the workflow branches off to notify a manager. You might have a step that checks resource availability using `list_users`. If nobody is free, the agent skips calling `create_task` and instead logs an alert. This MCP Server gives your agents the exact primitives needed to make those routing decisions.

Deploy Custom CZQL Pipelines Anywhere

Running advanced Clarizen Query Language shouldn't tie you to a specific cloud provider. Mastra packages your agent and its tools into a single unit you can deploy anywhere with one command. Your workflow executes `run_query` to pull highly specific portfolio metrics. Because you spread `mcpClient.listTools()` directly into your agent configuration, those complex data pulls become native actions in your automated reports.

Setup guide

Set up AdaptiveWork (Clarizen) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All AdaptiveWork (Clarizen) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "adaptivework-clarizen-mcp-client",
  servers: {
    "adaptivework-clarizen-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "AdaptiveWork (Clarizen) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to AdaptiveWork (Clarizen) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent AdaptiveWork (Clarizen) transactions"
);
console.log(result.text);

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 Mastra AI

Initialize a new `MCPClient` and pass your Vinkius URL into the servers object. Mastra auto-detects the streamable HTTP transport. From there, just spread the exposed tools into your agent's definition.

You certainly can. You can set `requireToolApproval` on destructive actions like `create_task`. The workflow pauses, waits for a human to review the parent ID and task name, and only proceeds once approved.

The framework's built-in workflow engine uses exponential backoff. If a heavy CZQL query fails, the MCP Server automatically waits and retries without you writing custom error handling logic.

No. The MCP framework automatically negotiates between SSE and HTTP transports based on the server's capabilities. You just provide the endpoint URL.

Vinkius processes your task names, parent IDs, and resource assignments through an ephemeral zero-trust architecture. The container executes the tool call and immediately destroys the environment. We never store your project structures.

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