How to Use the Asana MCP in OpenAI Agents SDK

Q: How do I connect Asana to my OpenAI Agents SDK project using this MCP Server?

You pass the Vinkius URL to the MCPServerStreamableHttp constructor. Then you add that server instance to the mcpservers list when you create your Agent. The SDK handles the rest, automatically discovering all the Asana tools.

Q: Can I create Asana tasks directly from an OpenAI Agent?

Yes, absolutely. Your agent just needs to invoke the createtask tool with the required details like project ID and task name. The OpenAI Agents SDK can even use its built-in guardrails to ask for confirmation before creating the task.

Q: What's the best way to list all our Asana projects with the OpenAI Agents SDK?

The agent should use the listworkspaces tool first, then pass a workspace ID to listprojects. This two-step process ensures you're getting projects from the correct Asana workspace, which is critical for agents working in multi-workspace accounts.

Q: Can my agent update an existing Asana task's status via the MCP Server?

It can. The updatetask tool lets your agent change a task's name, description, assignee, or completion status. The agent needs the taskid of the task it wants to modify.

Build production agents that manage Asana. Your OpenAI Agents SDK auto-discovers every tool from this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Asana MCP to OpenAI Agents SDK

Create your Vinkius account to connect Asana 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 Asana with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create and Track Asana Tasks

Your agent can instantly act on requests to `create_task` in any Asana project. It can just as easily `update_task` to change assignees, due dates, or descriptions. No manual setup is required—the tools are discovered automatically. This MCP Server gives your agent the ground truth. Use `get_task` to pull the latest details or `list_stories` to see a task's full history. The OpenAI SDK's built-in tracing lets you review every action, ensuring your agent behaves exactly as you designed it.

Navigate Projects with Your MCP Server

Before an agent can act, it needs to understand the landscape. This toolset lets it map out your entire Asana setup. It starts with `list_workspaces`, drills down into projects with `list_projects`, and inspects their structure using `list_sections`. This is perfect for multi-agent systems. One agent can specialize in discovery, building a complete picture of your projects. It then hands off a precise target—a specific task ID in a specific section—to another agent that specializes in execution.

Find Exactly What You Need

Stop asking your agent to guess. Give it the `search_tasks` tool. It can run targeted queries across an entire workspace to find exactly what you're looking for, filtering by text, status, or tags from `list_tags`. Precision is critical in production. The SDK's guardrails can validate the output of a search before the agent takes action. That's how you prevent it from accidentally updating the wrong 'Q4 Report' task.

Setup guide

Set up Asana 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 Asana tools at runtime.
3

Create your Agent

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

Run the agent

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

You pass the Vinkius URL to the `MCPServerStreamableHttp` constructor. Then you add that server instance to the `mcp_servers` list when you create your `Agent`. The SDK handles the rest, automatically discovering all the Asana tools.

Yes, absolutely. Your agent just needs to invoke the `create_task` tool with the required details like project ID and task name. The OpenAI Agents SDK can even use its built-in guardrails to ask for confirmation before creating the task.

The agent should use the `list_workspaces` tool first, then pass a workspace ID to `list_projects`. This two-step process ensures you're getting projects from the correct Asana workspace, which is critical for agents working in multi-workspace accounts.

It can. The `update_task` tool lets your agent change a task's name, description, assignee, or completion status. The agent needs the `task_id` of the task it wants to modify.

This server only touches data required by the tools. That includes your user info (`get_me`), project structure like tasks and sections, and a task's activity feed (`list_stories`). Vinkius processes each request in a zero-trust, ephemeral sandbox that is destroyed immediately after, ensuring none of your Asana data is stored.

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