> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent with Zapier nla integration

> Integrate with the Agent with Zapier nla tool using LangChain JavaScript.

<Warning>
  This module has been deprecated and is no longer supported. The documentation below will not work in versions 0.2.0 or later.
</Warning>

Full docs here: [https://nla.zapier.com/start/](https://nla.zapier.com/start/)

**Zapier Natural Language Actions** gives you access to the 5k+ apps and 20k+ actions on Zapier's platform through a natural language API interface.

NLA supports apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot, Google Sheets, Microsoft Teams, and thousands more apps: [https://zapier.com/apps](https://zapier.com/apps)

Zapier NLA handles ALL the underlying API auth and translation from natural language --> underlying API call --> return simplified output for LLMs. The key idea is you, or your users, expose a set of actions via an oauth-like setup window, which you can then query and execute via a REST API.

NLA offers both API Key and OAuth for signing NLA API requests.

Server-side (API Key): for quickly getting started, testing, and production scenarios where LangChain will only use actions exposed in the developer's Zapier account (and will use the developer's connected accounts on Zapier.com)

User-facing (Oauth): for production scenarios where you are deploying an end-user facing application and LangChain needs access to end-user's exposed actions and connected accounts on Zapier.com

Attach NLA credentials via either an environment variable (`ZAPIER_NLA_OAUTH_ACCESS_TOKEN` or `ZAPIER_NLA_API_KEY`) or refer to the params argument in the API reference for `ZapierNLAWrapper`.

Review [auth docs](https://docs.zapier.com/platform/build/auth) for more details.

The example below demonstrates how to use the Zapier integration as an Agent:

<Tip>
  See [this section for general instructions on installing LangChain packages](/oss/javascript/langchain/install).
</Tip>

```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
npm install @langchain/openai @langchain/core
```

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { OpenAI } from "@langchain/openai";
import { ZapierNLAWrapper } from "@langchain/classic/tools";
import {
  initializeAgentExecutorWithOptions,
  ZapierToolKit,
} from "@langchain/classic/agents";

const model = new OpenAI({ temperature: 0 });
const zapier = new ZapierNLAWrapper();
const toolkit = await ZapierToolKit.fromZapierNLAWrapper(zapier);

const executor = await initializeAgentExecutorWithOptions(
  toolkit.tools,
  model,
  {
    agentType: "zero-shot-react-description",
    verbose: true,
  }
);
console.log("Loaded agent.");

const input = `Summarize the last email I received regarding Silicon Valley Bank. Send the summary to the #test-zapier Slack channel.`;

console.log(`Executing with input "${input}"...`);

const result = await executor.invoke({ input });

console.log(`Got output ${result.output}`);
```

## Related

* Tool [conceptual guide](/oss/javascript/langchain/tools)
* Tool [how-to guides](/oss/javascript/langchain/tools)

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/javascript/integrations/tools/zapier_agent.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>