Asana Extension

This tutorial covers how to add the Asana MCP Server as a Goose extension to enable task automation, project tracking, and team collaboration.

TLDR

Goose Desktop
Goose CLI

Launch the installer

Command

npx -y @roychri/mcp-server-asana

Environment Variable

ASANA_ACCESS_TOKEN: <YOUR_TOKEN>

Configuration

info

Note that you'll need Node.js installed on your system to run this command, as it uses npx.

Goose Desktop
Goose CLI

Launch the installer
Press Yes to confirm the installation
Obtain a Asana Access Token and paste it in

info

See Asana's developer docs if you need detailed instructions on creating an access token.

Click Save Configuration
Scroll to the top and click Exit from the upper left corner

Run the configure command:

goose configure

Choose to add a Command-line Extension

  ┌   goose-configure 
  │
  ◇  What would you like to configure?
  │  Add Extension (Connect to a new extension) 
  │
  ◆  What type of extension would you like to add?
  │  ○ Built-in Extension 
  │  ● Command-line Extension (Run a local command or script)
  │  ○ Remote Extension 
  └ 

Give your extension a name

  ┌   goose-configure 
  │
  ◇  What would you like to configure?
  │  Add Extension (Connect to a new extension) 
  │
  ◇  What type of extension would you like to add?
  │  Command-line Extension 
  │
  ◆  What would you like to call this extension?
  │  Asana
  └ 

Enter the command

  ┌   goose-configure 
  │
  ◇  What would you like to configure?
  │  Add Extension (Connect to a new extension) 
  │
  ◇  What type of extension would you like to add?
  │  Command-line Extension 
  │
  ◇  What would you like to call this extension?
  │  Asana
  │
  ◆  What command should be run?
  │  npx -y @roychri/mcp-server-asana
  └ 

Enter the number of seconds Goose should wait for actions to complete before timing out. Default is 300s

┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension (Connect to a new extension) 
│
◇  What type of extension would you like to add?
│  Command-line Extension 
│
◇  What would you like to call this extension?
│  Asana
│
◇  What command should be run?
│  npx -y @roychri/mcp-server-asana
│
◆  Please set the timeout for this tool (in secs):
│  300
│
└ 

Choose to add a description. If you select "Yes" here, you will be prompted to enter a description for the extension.

┌   goose-configure 
│
◇  What would you like to configure?
│  Add Extension (Connect to a new extension) 
│
◇  What type of extension would you like to add?
│  Command-line Extension 
│
◇  What would you like to call this extension?
│  Asana
│
◇  What command should be run?
│  npx -y @roychri/mcp-server-asana
│
◇  Please set the timeout for this tool (in secs):
│  300
│
◇  Would you like to add a description?
│  No
│
└ 

Obtain a Asana Access Token and paste it in.

info

See Asana's developer docs if you need detailed instructions on creating an access token.

 ┌   goose-configure 
 │
 ◇  What would you like to configure?
 │  Add Extension (Connect to a new extension) 
 │
 ◇  What type of extension would you like to add?
 │  Command-line Extension 
 │
 ◇  What would you like to call this extension?
 │  Asana
 │
 ◇  What command should be run?
 │  npx -y @roychri/mcp-server-asana
 │     
 ◇  Please set the timeout for this tool (in secs):
 │  300
 │
 ◇  Would you like to add a description?
 │  No
 │    
 ◆  Would you like to add environment variables?
 │  Yes 
 │
 ◇  Environment variable name:
 │  ASANA_ACCESS_TOKEN
 │
 ◇  Environment variable value:
 │  ▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪
 │
 ◇  Add another environment variable?
 │  No 
 └  Added Asana extension

Example Usage

LLM

OpenAI's GPT-4o was used for this task. There's an open bug for Amazon Bedrock models.

Goose Prompt

Goose, I have one hour. Look through uncompleted tasks assigned to me in Asana and show me ones that you estimate will take an hour or less. Order them by deadline.

Goose Output

Note that IDs have been changed to generic ones

CLI

Tool Calls

─── asana_search_tasks | abcdefgh ──────────────────────────

assignee.any: me

completed: false

workspace: 1234567890123