Apify CLI for AI Agents

Framework Integration Gradient
Apify Logo
CLI Logo
divider

Introduction

CLIs are eating MCPs. The industry is converging on the very same idea. MCPs for all their merit can be token hungry, slow, and unreliable for complex tool chaining. However, coding agents have become incredibly good at working with CLIs, and in fact they are far more comfortable working with CLI tools than MCP.

With Composio's Universal CLI, your coding agents can talk to over 850+ SaaS applications. With Apify, agents can create a new dataset for scraped results, fetch items from a specific apify dataset, get details of your latest apify actor, and more — all without worrying about authentication.

This guide walks you through Composio Universal CLI and explains how you can connect it with coding agents like Claude Code, Codex, OpenCode, etc, for end-to-end Apify automation.

Also integrate Apify with

What is Universal CLI and why use it?

The idea behind building the universal CLI is to give agents a single command interface to interact with all your external applications. Here's what you'll get with it:

  • Agent-friendly: Coding agents like Claude Code, Codex, and OpenCode can use CLI tools natively — no MCP setup required.
  • Authentication handled: Connect once via OAuth or API Key, and all CLI commands work with your credentials automatically.
  • Tool discovery: Search, inspect, and execute 20,000+ tools across 850+ apps from one interface.
  • Trigger support: Use triggers to listen for events across your apps, powered by real-time webhooks or polling under the hood.
  • Type generation: Generate typed schemas for autocomplete and type safety in your projects.

Prerequisites

Install the Composio CLI, authenticate, and initialize your project:

bash
# Install the Composio CLI
curl -fsSL https://composio.dev/install | bash

# Authenticate with Composio
composio login

During login you'll be redirected to sign in page, finish the complete flow and you're all set.

Composio CLI authentication flow

Connecting Apify to Coding Agents via Universal CLI

Once it is installed, it's essentially done. Claude Code, Codex, OpenCode, OpenClaw, or any other agent will be able to access the CLI. A few steps to give agents access to your apps.

  1. Launch your Coding Agent — Claude Code, Codex, OpenCode, anything you prefer.
  2. Prompt it to "Authenticate with Apify"
  3. Complete the authentication and authorization flow and your Apify integration is all set.
  4. Start asking anything you want.

Supported Tools & Triggers

Tools
Create ActorTool to create a new actor with specified configuration.
Create DatasetTool to create a new dataset.
Create Actor TaskTool to create a new actor task with specified settings.
Create Task WebhookTool to create a webhook for an actor task.
Delete ActorTool to delete an actor permanently.
Delete WebhookTool to delete a webhook by its id.
Get Actor DetailsTool to get details of a specific actor.
Get all webhooksTool to get a list of all webhooks created by the user.
Get dataset itemsTool to retrieve items from a dataset.
Get Default BuildTool to get the default build for an actor.
Get Key-Value RecordTool to retrieve a record from a key-value store.
Get list of buildsTool to get a list of builds for a specific actor.
Get list of runsTool to get a list of runs for a specific actor.
Get list of task runsTool to get a list of runs for a specific actor task.
Get list of tasksTool to fetch a paginated list of tasks belonging to the authenticated user.
Get list of task webhooksTool to get a list of webhooks for a specific actor task.
Get logTool to retrieve logs for a specific actor run or build.
Get OpenAPI DefinitionTool to get the openapi definition for a specific actor build.
Get Task InputTool to retrieve the input configuration of a specific task.
Resurrect RunTool to resurrect a finished actor run.
Run Actor AsynchronouslyTool to run a specific actor asynchronously.
Run Actor SyncTool to run a specific actor synchronously with input and return its output record.
Run Actor Sync & Get Dataset ItemsTool to run an actor synchronously and retrieve its dataset items.
Run Task AsynchronouslyTool to run a specific actor task asynchronously.
Store Data in DatasetTool to store data items in a dataset.
Store Data in Key-Value StoreTool to create or update a record in a key-value store.
Update Key-Value StoreTool to update a key-value store's properties.
Update Task InputTool to update the input configuration of a specific actor task.

Universal CLI Commands for Apify

You can also manually execute CLI commands to interact with your Apify.

Connect your Apify account

Link your Apify account and verify the connection:

bash
# Connect your Apify account (opens OAuth flow)
composio connected-accounts link apify

# Verify the connection
composio connected-accounts list --toolkits apify

Discover Apify tools

Search and inspect available Apify tools:

bash
# List all available Apify tools
composio tools list --toolkit apify

# Search for Apify tools by action
composio tools search "apify"

# Inspect a tool's input schema
composio tools info APIFY_CREATE_ACTOR

Common Apify Actions

Create ActorTool to create a new actor with specified configuration

bash
composio tools execute APIFY_CREATE_ACTOR \
  --name "my-new-actor"

Create DatasetTool to create a new dataset

bash
composio tools execute APIFY_CREATE_DATASET \
  --name "my-dataset"

Create Actor TaskTool to create a new actor task with specified settings

bash
composio tools execute APIFY_CREATE_TASK \
  --name "my-recurring-task" \
  --actId "john~my-actor"

Create Task WebhookTool to create a webhook for an actor task

bash
composio tools execute APIFY_CREATE_TASK_WEBHOOK \
  --condition "<object>" \
  --eventTypes "ACTOR.TASK.RUN.SUCCEEDED" \
  --requestUrl "https://example.com/webhook"

Generate Type Definitions

Generate typed schemas for Apify tools to get autocomplete and type safety in your project:

bash
# Auto-detect language
composio generate --toolkits apify

# TypeScript
composio ts generate --toolkits apify

# Python
composio py generate --toolkits apify

Tips & Tricks

  • Always inspect a tool's input schema before executing: composio tools info <TOOL_NAME>
  • Pipe output with jq for better readability: composio tools execute TOOL_NAME -d '{}' | jq
  • Set COMPOSIO_API_KEY as an environment variable for CI/CD pipelines
  • Use composio dev logs tools to inspect execution logs and debug issues

Next Steps

  • Try asking your coding agent to perform various Apify operations
  • Explore cross-app workflows by connecting more toolkits
  • Set up triggers for real-time automation
  • Use composio generate for typed schemas in your projects

How to build Apify MCP Agent with another framework

FAQ

What is the Composio Universal CLI?

The Composio Universal CLI is a single command-line interface that lets coding agents and developers interact with 850+ SaaS applications. It handles authentication, tool discovery, action execution, and trigger setup — all from the terminal, without needing to configure MCP servers.

Which coding agents work with the Composio CLI?

Any coding agent that can run shell commands works with the Composio CLI — including Claude Code, Codex, OpenCode, OpenClaw, and others. Once the CLI is installed, agents automatically discover and use the composio commands to interact with Apify and other connected apps.

How is the CLI different from using an MCP server for Apify?

MCP servers require configuration and can be token-heavy for complex workflows. The CLI gives agents a direct, lightweight interface — no server setup needed. Agents simply call composio commands like any other shell tool. It's faster to set up, more reliable for multi-step tool chaining, and works natively with how coding agents already operate.

How safe is my Apify data when using the Composio CLI?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Apify data and credentials are handled as safely as possible. You can also bring your own OAuth credentials for full control.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.