How to Use the Infinity Work Manager MCP in OpenAI Agents SDK

Q: How do I register the Infinity Work Manager MCP server in the OpenAI Agents SDK?

Install openai-agents via pip, then instantiate MCPServerStreamableHttp using your Vinkius endpoint. Pass this instance inside the mcpservers list when initializing your Agent class. The SDK automatically discovers all 15 MCP tools like createitem and listitems at runtime.

Run multi-agent workflows that safely manipulate Infinity Work Manager boards using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Infinity Work Manager MCP to OpenAI Agents SDK

Create your Vinkius account to connect Infinity Work Manager 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 Infinity Work Manager with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Board Management

The `create_board` tool lets your agent initialize workspace environments dynamically before handing off tasks to specialized workers. You pass raw board parameters to the OpenAI Agents SDK using this MCP server, and the runtime handles the instantiation without manual API calls. This avoids complex routing logic in your orchestration layer. Once the board exists, your agent uses `create_folder` to structure the workspace. Specialized agents then receive the new structure to populate tasks, keeping your team's workspace organized without human intervention.

Guarded Task Updates with OpenAI Agents SDK

The `update_item` tool executes state transitions on your tasks with absolute safety guaranteed by the SDK's runtime guardrails using the MCP standard. When your agent attempts to modify a status, the SDK intercepts the payload to check it against your validation rules. This prevents the agent from corrupting board states or setting invalid attribute values. If a tool call fails validation, the SDK traces the error back to the OpenAI dashboard. You see exactly what payload `update_item` received, making debugging fast and painless.

Automated Workspace Auditing via MCP Server

The `list_workspaces` tool retrieves all accessible workspaces so your agent can audit activity across your entire organization. By combining this with `list_boards`, the agent maps out every active project file without manual configuration. The agent then relies on `list_comments` to extract feedback loops and flag blocked items. This gives your team a clear view of bottlenecks directly inside your custom dashboard.

Setup guide

Set up Infinity Work Manager 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 Infinity Work Manager tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Infinity Work Manager 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="Infinity Work Manager Agent",
            instructions="You have access to Infinity Work Manager 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 Infinity. 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 Infinity Work Manager 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 Infinity Work Manager MCP in OpenAI Agents SDK

Install `openai-agents` via pip, then instantiate `MCPServerStreamableHttp` using your Vinkius endpoint. Pass this instance inside the `mcp_servers` list when initializing your Agent class. The SDK automatically discovers all 15 MCP tools like `create_item` and `list_items` at runtime.

Yes, you should configure the SDK's built-in retry mechanisms to catch rate limits during heavy execution of `update_item` or `create_comment`. The SDK intercepts HTTP errors from the server and backs off automatically. This keeps your automated pipeline running without crashing.

You control access by managing the API token passed to your Vinkius endpoint, which dictates which workspaces `list_workspaces` can return. You can also define system prompts in the SDK to prevent the agent from executing `delete_item` on critical boards.

Use the OpenAI developer dashboard to inspect the full execution trace of the MCP tool call. You'll see the exact JSON payload sent to `create_item` and the raw error response returned by the API.

Your board schemas, task names, and comments touch only the Vinkius zero-trust sandbox and the Infinity API. Vinkius runs the integration in isolated V8 environments, meaning your project data is never stored or used to train models.

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