How to Use the AdaptiveWork (Clarizen) MCP in OpenAI Agents SDK

Run production-ready OpenAI Agents SDK workflows that directly manipulate your AdaptiveWork projects with built-in guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect AdaptiveWork (Clarizen) to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit AdaptiveWork projects using OpenAI Agents SDK

The `list_projects` tool lets your OpenAI agent pull live portfolio statuses directly into your multi-agent routing loop. Your agent checks active project states, analyzes delays, and uses `get_project_details` to isolate specific bottlenecks without human intervention. This MCP setup allows your coordinator agent to hand off heavy analysis to a specialized analyst agent. The agent parses the raw metadata, confirms progress metrics, and logs the execution trace directly to your OpenAI dashboard.

Dispatch granular tasks and check team availability

The `create_task` tool executes exact project updates by binding new tasks directly to their parent structures in Clarizen. Your agent queries the current workforce using `list_users` to match open workloads with available team members. By declaring these tools in your Python agent constructor, the SDK handles schema validation before executing any write operations. If an agent attempts to assign work to an inactive user, the built-in guardrails block the call instantly.

Run raw CZQL queries safely from python agents

The `run_query` tool exposes direct Clarizen Query Language execution to your autonomous agent pipelines. You pass custom CZQL strings to extract deep relational data that standard endpoints hide. To keep operations safe, the OpenAI Agents SDK monitors these raw queries against your predefined safety policies. You get raw JSON payloads returned directly to your agent's context window while maintaining strict read-only boundaries where needed.

Setup guide

Set up AdaptiveWork (Clarizen) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all AdaptiveWork (Clarizen) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AdaptiveWork (Clarizen) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AdaptiveWork (Clarizen) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="AdaptiveWork (Clarizen) Agent",
            instructions="You have access to AdaptiveWork (Clarizen) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install openai-agents and instantiate the MCPServerStreamableHttp class with your Vinkius endpoint. Pass this server instance inside the mcp_servers list when constructing your Agent. The SDK automatically discovers all six tools at runtime.

Yes, you control this by defining specific tool filters or using distinct agent instances for read and write tasks. For example, you can build a read-only agent that only receives `list_projects` while restricting `create_task` to a supervisor agent.

The SDK matches the JSON schema exposed by the Vinkius MCP Server against the arguments generated by the model. If the model spits out bad parameters for `create_task`, the SDK catches the error before hitting the Clarizen API.

The SDK captures the API error from the Vinkius proxy and feeds the failure state back to your agent. This allows the model to self-correct its CZQL syntax for `run_query` and try again.

All task descriptions, user emails, and project timelines are processed inside an ephemeral, zero-trust V8 isolate sandbox. Vinkius handles the underlying OAuth handshake, meaning your raw API credentials never touch the client-side code.

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