Skip to main content

Action Availability

This document provides an overview of which Agent.ai actions are available across different platforms and SDKs, along with installation instructions for each package.

Installation Instructions

Python SDK

The Agent.ai Python SDK provides a simple way to interact with the Agent.ai Actions API. Installation:
pip install agentai
Links:

JavaScript SDK

The Agent.ai JavaScript SDK allows you to integrate Agent.ai actions into your JavaScript applications. Installation:
# Using yarn
yarn add @agentai/agentai

# Using npm
npm install @agentai/agentai
Links:

MCP Server

The MCP (Multi-Channel Platform) Server provides a server-side implementation of all API functions. Installation:
# Using yarn
yarn add @agentai/mcp-server

# Using npm
npm install @agentai/mcp-server
Links: Legend:
  • ✅ - Feature is available
  • ❌ - Feature is not available
Notes:
  • The Builder UI has the most comprehensive set of actions available
  • The MCP Server implements all API functions
  • The Python and JavaScript SDKs currently implement the same set of actions
  • Some actions are only available in the Builder UI and are not exposed via the API yet, but we plan to get to 100% parity scross our packaged offerings.

Action Availability Table

ActionDocsAPIBuilder UIAPIMCP ServerPython SDKJS SDK
Get User InputDocs-
Get User ListDocs-
Get User FilesDocs-
Get User Knowledge Base and FilesDocs-
Web Page ContentDocsAPI
Web Page ScreenshotDocsAPI
YouTube TranscriptDocsAPI
YouTube Channel DataDocsAPI
Get Twitter UsersDocsAPI
Google News DataDocsAPI
YouTube Search ResultsDocsAPI
Search ResultsDocsAPI
Search HubSpot (V2)Docs-
Lookup HubSpot Object (V2)Docs-
Create HubSpot Object (V2)Docs-
Update HubSpot Object (V2)Docs-
Get Timeline Events (V2)Docs-
Create Timeline Event (V2)Docs-
Get Engagements (V2)Docs-
Create Engagement (V2)Docs-
Recent TweetsDocsAPI
LinkedIn ProfileDocsAPI
Get LinkedIn ActivityDocsAPI
Enrich with Breeze IntelligenceDocsAPI
Company Earnings InfoDocsAPI
Company Financial ProfileDocsAPI
Domain InfoDocsAPI
Get Data from Builder’s Knowledge BaseDocs-
Get Data from User’s Uploaded FilesDocs-
Set VariableDocs-
Add to ListDocs-
Click Go to ContinueDocs-
Use GenAI (LLM)DocsAPI
Generate ImageDocsAPI
Generate Audio OutputDocsAPI
Orchestrate TasksDocs-
Orchestrate AgentsDocs-
Convert FileDocsAPI
Continue or Exit WorkflowDocs-
If/Else StatementDocs-
For LoopDocs-
End If/Else/For StatementDocs-
Wait for User ConfirmationDocs-
Get Assigned CompanyDocs-
Query HubSpot CRMDocs-
Create Web PageDocs-
Get HubDB DataDocs-
Update HubDBDocs-
Get ConversationDocs-
Start Browser OperatorDocsAPI
Browser Operator ResultsDocsAPI
Invoke Web APIDocsAPI
Invoke Other AgentDocsAPI
Show User OutputDocs-
Send MessageDocs-
Create Blog PostDocs-
Save To Google DocDocs-
Save To FileDocsAPI
Save To Google SheetDocs-
Format TextDocs-
Store Variable to DatabaseDocsAPI
Get Variable from DatabaseDocsAPI
Bluesky PostsDocsAPI
Search Bluesky PostsDocsAPI
Post to BlueskyDocs-
Get Instagram ProfileDocsAPI
Get Instagram FollowersDocsAPI
Call Serverless FunctionDocs-

New in API v1.1.0

The v1.1.0 API surface introduces a large set of new capabilities across people intelligence, the LinkedIn suite, calendar/email, agent memory, richer HubSpot access, financial data, and rendered-report builders. Each row below links to its builder documentation and lives in the API Reference.
ActionDocsAPIBuilder UI
Enrich PersonDocs
Contact ResearchDocs
Comprehensive Contact IntelligenceDocs
Find LinkedIn ProfileDocs
Get LinkedIn Company ProfileDocs
Get LinkedIn Company PostsDocs
Get LinkedIn Posts (by URL)Docs
Get LinkedIn Job PostingDocs
Search LinkedIn PeopleDocs
Search LinkedIn JobsDocs
Search LinkedIn Posts by KeywordDocs
Render LinkedIn Sentiment ReportDocs
Get Calendar Events ListDocs
Enrich Calendar EventDocs
Fetch Relevant Gmail ThreadsDocs
Process VideoDocs
Save Agent MemoryDocs
Look Up Agent MemoriesDocs
List Agent MemoriesDocs
Get HubSpot OwnersDocs
Get HubSpot ContactDocs
Get HubSpot CompanyDocs
Get HubSpot ObjectDocs
Create Tabbed ReportDocs

Agent Packs (orchestrated pipelines)

Beyond atomic actions, v1.1.0 adds Agent Packs — purpose-built multi-step pipelines that ship as a group of related endpoints. See the Agent Packs overview for the full list, which includes: Each pack typically exposes both an orchestrated one-call endpoint (run_full_* / run_optimized_pipeline) and a set of granular step actions you can call independently from the builder.

Summary

  • UI Builder supports the full action surface — all of the above.
  • API (v1.1.0) now spans over 180 endpoints across core actions and Agent Pack pipelines — see the API Reference for the complete list.
  • MCP Server supports the same core actions as the API.
  • Python SDK and JavaScript SDK currently cover the core data retrieval and AI generation actions; additional coverage rolls out over time.
The Python and JavaScript SDKs currently implement the same set of core data retrieval and AI generation functions as the builder, but there are some actions that either don’t make sense to implement via our API (i.e. get user input) or aren’t useful as standalone actions (i.e. for loops). You can always implement an agent through the builder UI and invoke it via API or daisy chain agents together.