> ## 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.

# OpenAPI toolkit integration

> Integrate with the OpenAPI toolkit using LangChain JavaScript.

<Warning>
  This agent can make requests to external APIs. Use with caution, especially when granting access to users.

  Be aware that this agent could theoretically send requests with provided credentials or other sensitive data to unverified or potentially malicious URLs --although it should never in theory.

  Consider adding limitations to what actions can be performed via the agent, what APIs it can access, what headers can be passed, and more.

  In addition, consider implementing measures to validate URLs before sending requests, and to securely handle and protect sensitive data such as credentials.
</Warning>

This will help you getting started with `OpenApiToolkit` [OpenAPI toolkit](/oss/javascript/integrations/tools/openapi). `OpenApiToolkit` now lives in `@langchain/classic`. For migration details, see the [LangChain v1 migration guide](/oss/javascript/migrate/langchain-v1).

The `OpenAPIToolkit` has access to the following tools:

| Name            | Description                                                                                                                                                                                                                                                                                                                                                                                       |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `requests_get`  | A portal to the internet. Use this when you need to get specific content from a website. Input should be a URL string (i.e. "[www.google.com](https://www.google.com)"). The output will be the text response of the GET request.                                                                                                                                                                 |
| `requests_post` | Use this when you want to POST to a website. Input should be a json string with two keys: "url" and "data". The value of "url" should be a string, and the value of "data" should be a dictionary of key-value pairs you want to POST to the URL as a JSON body. Be careful to always use double quotes for strings in the json string. The output will be the text response of the POST request. |
| `json_explorer` | Can be used to answer questions about the openapi spec for the API. Always use this tool before trying to make a request. Example inputs to this tool: 'What are the required query parameters for a GET request to the /bar endpoint?' 'What are the required parameters in the request body for a POST request to the /foo endpoint?' Always give this tool a specific question.                |

## Setup

This toolkit requires an OpenAPI spec file. The LangChain.js repository has a [sample OpenAPI spec file in the `examples` directory](https://github.com/langchain-ai/langchainjs/blob/cc21aa29102571204f4443a40b53d28581a12e30/examples/openai_openapi.yaml). You can use this file to test the toolkit.

If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](/langsmith/observability) API key by uncommenting below:

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
process.env.LANGSMITH_TRACING="true"
process.env.LANGSMITH_API_KEY="your-api-key"
```

### Installation

This toolkit lives in the `langchain` package:

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

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add langchain @langchain/core
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add langchain @langchain/core
  ```
</CodeGroup>

## Instantiation

Now we can instantiate our toolkit. First, we need to define the LLM we would like to use in the toolkit.

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
// @lc-docs-hide-cell

import { ChatOpenAI } from "@langchain/openai";
const llm = new ChatOpenAI({
  model: "gpt-5.4-mini",
  temperature: 0,
})
```

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { OpenApiToolkit } from "@langchain/classic/agents/toolkits"
import * as fs from "fs";
import * as yaml from "js-yaml";
import { JsonSpec, JsonObject } from "@langchain/classic/tools";

// Load & convert the OpenAPI spec from YAML to JSON.
const yamlFile = fs.readFileSync("../../../../../examples/openai_openapi.yaml", "utf8");
const data = yaml.load(yamlFile) as JsonObject;
if (!data) {
  throw new Error("Failed to load OpenAPI spec");
}

// Define headers for the API requests.
const headers = {
  "Content-Type": "application/json",
  Authorization: `Bearer ${process.env.OPENAI_API_KEY}`,
};

const toolkit = new OpenApiToolkit(new JsonSpec(data), llm, headers);
```

## Tools

View available tools:

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const tools = toolkit.getTools();

console.log(tools.map((tool) => ({
  name: tool.name,
  description: tool.description,
})))
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[
  {
    name: 'requests_get',
    description: 'A portal to the internet. Use this when you need to get specific content from a website.\n' +
      '  Input should be a url string (i.e. "https://www.google.com"). The output will be the text response of the GET request.'
  },
  {
    name: 'requests_post',
    description: 'Use this when you want to POST to a website.\n' +
      '  Input should be a json string with two keys: "url" and "data".\n' +
      '  The value of "url" should be a string, and the value of "data" should be a dictionary of\n' +
      '  key-value pairs you want to POST to the url as a JSON body.\n' +
      '  Be careful to always use double quotes for strings in the json string\n' +
      '  The output will be the text response of the POST request.'
  },
  {
    name: 'json_explorer',
    description: '\n' +
      'Can be used to answer questions about the openapi spec for the API. Always use this tool before trying to make a request. \n' +
      'Example inputs to this tool: \n' +
      "    'What are the required query parameters for a GET request to the /bar endpoint?'\n" +
      "    'What are the required parameters in the request body for a POST request to the /foo endpoint?'\n" +
      'Always give this tool a specific question.'
  }
]
```

## Use within an agent

First, ensure you have LangGraph installed:

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @langchain/langgraph
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @langchain/langgraph
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @langchain/langgraph
  ```
</CodeGroup>

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { createAgent } from "@langchain/classic"

const agentExecutor = createAgent({ llm, tools });
```

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
const exampleQuery = "Make a POST request to openai /chat/completions. The prompt should be 'tell me a joke.'. Ensure you use the model 'gpt-5.4-mini'."

const stream = await agentExecutor.streamEvents(
  { messages: [["user", exampleQuery]] },
  { version: "v3" },
);

for await (const snapshot of stream.values) {
  const lastMsg = snapshot.messages[snapshot.messages.length - 1];
  if (lastMsg.tool_calls?.length) {
    console.dir(lastMsg.tool_calls, { depth: null });
  } else if (lastMsg.content) {
    console.log(lastMsg.content);
  }
}
```

```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[
  {
    name: 'requests_post',
    args: {
      input: '{"url":"https://api.openai.com/v1/chat/completions","data":{"model":"gpt-5.4-mini","messages":[{"role":"user","content":"tell me a joke."}]}}'
    },
    type: 'tool_call',
    id: 'call_1HqyZrbYgKFwQRfAtsZA2uL5'
  }
]
{
  "id": "chatcmpl-9t36IIuRCs0WGMEy69HUqPcKvOc1w",
  "object": "chat.completion",
  "created": 1722906986,
  "model": "gpt-5.4-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Why don't skeletons fight each other? \n\nThey don't have the guts!"
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 15,
    "total_tokens": 27
  },
  "system_fingerprint": "fp_48196bc67a"
}

Here's a joke for you:

**Why don't skeletons fight each other?**
They don't have the guts!
```

***

## API reference

There is currently no dedicated API reference page for `OpenApiToolkit` in `@langchain/classic`. For implementation details, see [`OpenApiToolkit` source in `langchainjs`](https://github.com/langchain-ai/langchainjs/blob/main/libs/langchain-classic/src/agents/toolkits/openapi/openapi.ts).

***

<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/openapi.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>