Asana

The Asana auth provider enables tools and agents to call Asana APIs on behalf of a user. Behind the scenes, the Arcade Engine and the Asana auth provider seamlessly manage Asana OAuth 2.0 authorization for your users.

What’s documented here

This page describes how to use and configure Asana auth with Arcade.

This auth provider is used by:

• The Arcade Asana MCP Server, which provides pre-built tools for interacting with Asana
• Your app code that needs to call Asana APIs
• Or, your custom tools that need to call Asana APIs

Use Arcade’s Default Asana Auth Provider

Arcade offers a default Asana auth provider that you can use in the Arcade Cloud Platform. In this case, your users will see Arcade as the name of the application that’s requesting permission.

If you choose to use Arcade’s Asana auth, you don’t need to configure anything. Follow the Asana MCP Server examples to get started calling Asana tools.

Use Your Own Asana App Credentials

In a production environment, you will most likely want to use your own Asana app credentials. This way, your users will see your application’s name requesting permission.

You can use your own Asana credentials in both the Arcade Cloud Platform or in a self-hosted Arcade Engine instance.

Before showing how to configure your Asana app credentials, let’s go through the steps to create an Asana app.

Create an Asana App

Follow the documentation on Building an App with Asana . You may create a developer sandbox account  to test your app before moving to production.

When creating your app, use the following settings:

• Set an appropriate App name, description and icon. This will be visible to your users authorizing access to your app.
• Take note of the Client ID and Client Secret.
• In the OAuth settings:
  • Under “Redirect URLs”, click Add Redirect URL and add the redirect URL generated by Arcade (see below).
  • Under “Permission Scopes”, select “Full Permissions”
• In the “App Listing Details” section, optionally add more information about your app.
• In the “Manage Distribution” section, under “Choose a distribution method”, select “Any workspace”.
• Optionally, submit your app for the Asana team review.

Configuring your own Asana Auth Provider in Arcade

There are two ways to configure your Asana app credentials in Arcade:

1. From the Arcade Dashboard GUI
2. By editing the engine.yaml file directly (only possible with a self-hosted Arcade Engine)

We show both options step-by-step below.

export ASANA_CLIENT_ID="<your client ID>"
export ASANA_CLIENT_SECRET="<your client secret>"

ASANA_CLIENT_ID="<your client ID>"
ASANA_CLIENT_SECRET="<your client secret>"

auth:
  providers:
    - id: asana
      description: "Custom Asana provider"
      enabled: true
      type: oauth2
      client_id: ${env:ASANA_CLIENT_ID}
      client_secret: ${env:ASANA_CLIENT_SECRET}

Using the Arcade Asana MCP Servers

The Arcade Asana MCP Server provides tools to interact with various Asana objects, such as tasks, projects, teams, and users.

Refer to the MCP Server documentation and examples to learn how to use the MCP Server to build agents and AI apps that interact with Asana services.

Using Asana auth in app code

Use the Asana auth provider in your own agents and AI apps to get a user-scoped token for the Asana API. See authorizing agents with Arcade to understand how this works.

Use client.auth.start() to get a user token for the Asana API:

from arcadepy import Arcade
 
client = Arcade(base_url="https://api.arcade.dev")  # Automatically finds the `ARCADE_API_KEY` env variable
 
user_id = "{arcade_user_id}"
 
# Start the authorization process
auth_response = client.auth.start(
    user_id=user_id,
    provider="asana",
    scopes=["default"],
)
 
if auth_response.status != "completed":
    print("Please complete the authorization challenge in your browser:")
    print(auth_response.url)
 
# Wait for the authorization to complete
auth_response = client.auth.wait_for_completion(auth_response)
 
# Do something interesting with the token...
auth_token = auth_response.context.token

import { Arcade } from "@arcadeai/arcadejs";
 
const client = new Arcade({ baseURL: "https://api.arcade.dev" }); // Automatically finds the `ARCADE_API_KEY` env variable
 
const userId = "{arcade_user_id}";
 
// Start the authorization process
const authResponse = await client.auth.start(userId, "asana", {
  scopes: ["default"],
});
 
if (authResponse.status !== "completed") {
  console.log("Please complete the authorization challenge in your browser:");
  console.log(authResponse.url);
}
 
// Wait for the authorization to complete
const response = await client.auth.waitForCompletion(authResponse);
 
// Do something interesting with the token...
const auth_token = response.context.token;

You can use the auth token to call the Get multiple tasks endpoint  and read information about tasks, for example. Any Asana API endpoint can be called with the auth token.

Using Asana auth in custom tools

You can use the pre-built Arcade Asana MCP Server to quickly build agents and AI apps that interact with Asana.

If the pre-built tools in the Asana MCP Server don’t meet your needs, you can author your own custom tools that interact with Asana API.

Use the Asana() auth class to specify that a tool requires authorization with Asana. The authentication token needed to call the Asana API is available in the tool context through the context.get_auth_token_or_empty() method.

from typing import Annotated
 
import httpx
 
from arcade_tdk import ToolContext, tool
from arcade_tdk.auth import Asana
 
 
@tool(requires_auth=Asana(scopes=["default"]))
async def delete_task(
    context: ToolContext,
    task_id: Annotated[str, "The ID of the task to delete."],
) -> Annotated[dict, "Details of the deletion response"]:
    """Deletes a task."""
    url = f"https://api.asana.com/api/1.0/tasks/{task_id}"
    headers = {
        "Authorization": f"Bearer {context.get_auth_token_or_empty()}",
        "Accept": "application/json",
    }
 
    async with httpx.AsyncClient() as client:
        response = await client.delete(url, headers=headers)
        response.raise_for_status()
        return response.json()

If you are self-hosting Arcade, you will need to restart the Arcade Worker and the Engine for the new tool to be available.

Your new tool can be called like demonstrated below:

from arcadepy import Arcade
 
client = Arcade(base_url="https://api.arcade.dev")  # Automatically finds the `ARCADE_API_KEY` env variable
 
USER_ID = "{arcade_user_id}"
TOOL_NAME = "Asana.DeleteTask"
 
auth_response = client.tools.authorize(tool_name=TOOL_NAME, user_id=USER_ID)
 
if auth_response.status != "completed":
    print(f"Click this link to authorize: {auth_response.url}")
 
# Wait for the authorization to complete
client.auth.wait_for_completion(auth_response)
 
tool_input = {
    "task_id": "1234567890",
}
 
response = client.tools.execute(
    tool_name=TOOL_NAME,
    input=tool_input,
    user_id=USER_ID,
)
print(response.output.value)

import { Arcade } from "@arcadeai/arcadejs";
 
const client = new Arcade({ baseURL: "https://api.arcade.dev" }); // Automatically finds the `ARCADE_API_KEY` env variable
 
const USER_ID = "{arcade_user_id}";
const TOOL_NAME = "Asana.DeleteTask";
 
// Start the authorization process
const authResponse = await client.tools.authorize({
  tool_name: TOOL_NAME,
  user_id: USER_ID,
});
 
if (authResponse.status !== "completed") {
  console.log(`Click this link to authorize: ${authResponse.url}`);
}
 
// Wait for the authorization to complete
await client.auth.waitForCompletion(authResponse);
 
const toolInput = {
  task_id: "1234567890",
};
 
const response = await client.tools.execute({
  tool_name: TOOL_NAME,
  input: toolInput,
  user_id: USER_ID,
});
 
console.log(response.output.value);