Skill

Automate Actions with Zapier

A LlamaIndex tool that connects AI agents to Zapier's Natural Language Actions API, enabling agents to query and execute enabled Zapier actions using natural

Works with zapiergoogle drive

71
Spark score
out of 100
Updated 3 months ago
Version 1.0.0
Models

Add to Favorites

Why it matters

Leverage the Zapier Natural Language Actions API to automate tasks and access information across your connected applications through natural language commands.

Outcomes

What it gets done

01

List available Zapier actions.

02

Execute Zapier actions using natural language queries.

03

Integrate with Google Drive to find files.

04

Connect to your Zapier account via API key or OAuth token.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/li-tool-tools-zapier | bash

Capabilities

What this skill does

Extract

Pulls structured data fields from unstructured text.

Search the web

Searches the web and retrieves relevant sources.

Notify

Sends alerts or messages via email, Slack, or other channels.

Audit access

Reviews permissions and logs to flag unauthorized activity.

Overview

Zapier Tool

What it does

This tool connects to a Zapier account and provides access to the Natural Language Actions API. It allows agents to list actions you have enabled through Zapier and make natural language queries to execute those actions.

How it connects

Use this tool when you need your LlamaIndex agent to interact with Zapier actions you've already configured, such as querying files in Google Drive or executing other enabled automations through conversational commands.

Source README

Zapier Tool

This tool connects to a Zapier account and allows access to the natural language actions API. You can learn more about and enable the NLA API here: https://nla.zapier.com/start/

Usage

This tool has more extensive example usage documented in a Jupyter notebook here

Here's an example usage of the ZapierToolSpec.

from llama_index.tools.zapier import ZapierToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI


zapier_spec = ZapierToolSpec(api_key="sk-ak-your-key")
### Or
zapier_spec = ZapierToolSpec(api_key="oauth-token")

agent = FunctionAgent(
    tools=zapier_spec.to_tool_list(),
    llm=OpenAI(model="gpt-4.1"),
)

print(await agent.run("what actions are available"))
print(await agent.run("Can you find the taco night file in google drive"))

list_actions: Get the actions that you have enabled through zapier
natural_language_query: Make a natural language query to zapier

This loader is designed to be used as a way to load data as a Tool in a Agent.

FAQ

Common questions

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.