AIRO MCP server

The AIRO MCP server exposes Workato AIRO's full platform capabilities to MCP-compatible AI clients, including Claude Code, Claude Desktop, Cursor, ChatGPT, and Codex CLI. This enables you to build recipes, manage Genies, create MCP servers, and manage data table schema directly from your AI development environment using natural language.

AIRO as an MCP serverAIRO as an MCP server

How it works

The AIRO MCP server supports two authentication methods:

  • OAuth 2.0: Recommended for interactive clients. Your MCP client opens a browser window the first time you connect. The window displays Workato's authorization screen, which lists the permissions requested by the client. Click Authorize to complete the connection. Refer to Connect using OAuth 2.0 for the setup steps.
  • API token: Recommended for headless or configuration-driven setups. Pass a Workato API token as a bearer header. Refer to Connect using an API token for the setup steps.

The server exposes tools organized into the following categories:

CategoryWhat you can do
RecipesCreate, edit, search, and manage recipes, including step-level operations, field mapping, conditions, and connections
Skills and MCPConvert recipes to skills and create or manage MCP servers
Genies and knowledge basesCreate and configure Genies, manage knowledge bases, and assign knowledge sources
Blueprints and assetsWork with blueprints, asset maps, and asset metadata
DataCreate and manage data table schema
Jobs and testsInspect job history and manage test cases

Use the help tool within your MCP client to get detailed information about any specific tool, including input schemas and usage guidance.

The AIRO MCP server respects your Workato account permissions for OAuth 2.0 connections, or the permissions of the API client role for API token connections. All actions performed through the MCP server follow the same access controls as actions performed in the Workato platform.

The activity audit log attributes actions that the AIRO MCP server takes on your behalf to your user account with a (via AIRO) label.

Prerequisites

You must have the following before you configure the AIRO MCP server:

  • A Workato account with AIRO access
  • An MCP-compatible client installed, such as Claude Code, Claude Desktop, Cursor, ChatGPT, or Codex CLI

Some MCP client configurations use npx. These configurations require Node.js to be installed and available in your PATH. Run node -v in your terminal to verify your installation.

API token authentication also requires a Workato API token. Refer to Generate an API token for instructions.

Connect using OAuth 2.0

Complete the following steps to connect the AIRO MCP server to your MCP client using OAuth 2.0:

WORKSPACE AND ENVIRONMENT SCOPE

OAuth 2.0 scopes each AIRO MCP server connection to the Workato workspace and environment active in your browser session. Sign in to the target workspace and environment before you start authorization. Repeat the authorization steps for a different workspace or environment, or create a separate connection for each workspace and environment you need to access at the same time.

Connect using an API token

API token authentication requires a Workato API token.

Generate an API token

Complete the following steps to obtain an API token:

1

Sign in to Workato.

2

Go to Workspace admin > API clients > Client roles.

3

Open an existing client role or create a client role.

4

Enable the AIRO MCP feature for the role.

The AIRO MCP feature enabled in the Project assets list of a client roleEnable the AIRO MCP feature for the client role

5

Click Save changes.

6

Assign this client role to an existing API client, or select the role when you create a new API client.

7

Copy and securely store the API client token.

Configure your MCP client

Complete the steps for your MCP client:

Use cases

The following examples demonstrate common workflows with the AIRO MCP server.

Build and test a recipe

Use AIRO to create a multi-step recipe from a natural language description, then save and test it without leaving your development environment.

Create a recipe that syncs new Salesforce opportunities to Jira issues.
Add an OpenAI step to summarize the opportunity before creating the Jira issue.
Save the recipe and show me the test cases.

Create a genie with knowledge sources

Set up a genie and connect it to relevant knowledge bases so it can answer domain-specific questions.

Create a new genie called "Sales Intelligence" and assign the CRM knowledge base to it.

Build an MCP server

Create an MCP server from your workspace assets so other AI clients can connect to your tools.

Build an MCP server called "Sales Tools" using the lead enrichment and deal scoring skills from the Sales Automation project.

Investigate job failures

Inspect recent job history to diagnose errors in production recipes.

List the last 10 jobs for recipe 1555928 and show me any errors.

Manage a data table

Create a data table and define its schema without leaving your development environment.

Create a data table to store approver thresholds by region.

Last updated: