---
title: "Server-side tools (Vercel AI SDK)"
description: "Learn how to call server-side tools using the Vercel AI SDK."
canonical_url: "https://tiptap.dev/docs/ai/deprecated/agent/custom-llms/server-side-tools/vercel-ai-sdk"
---

# Server-side tools (Vercel AI SDK)

Learn how to call server-side tools using the Vercel AI SDK.

This guide explains how to call server-side tools using the [Vercel AI SDK](https://ai-sdk.dev). It presents an example of a tool that returns the weather in a given location.

First, define the tool in the [Vercel AI SDK tool format](https://ai-sdk.dev/docs/ai-sdk-core/tools-and-tool-calling):

```ts
import { z } from 'zod'
import { tool } from 'ai'

const weatherTool = tool({
  description: 'Get the weather in a location',
  parameters: z.object({
    location: z.string().describe('The location to get the weather for'),
  }),
  execute: async (args) => {
    // Get weather from an external API
    const result = await getWeather(args)
    return result
  },
})
```

Then, when you call the Vercel AI SDK, include the tool in the `tools` object.

Do not forget to set `maxSteps` to a value greater than 1, to enable [multi-step tool calls](https://ai-sdk.dev/docs/ai-sdk-core/tools-and-tool-calling#multi-step-calls-using-maxsteps). This parameter lets the AI call multiple tools in sequence. For example, it can call the tool to get the weather report, and then call a tool to edit the document with that information.

> **Use with Vercel AI SDK v4:**
>
> To use the Vercel AI SDK v4 instead of v5, import the `vercelAiSdkV4Adapter` instead of
> `vercelAiSdkAdapter`.

```ts
import {
  AiAgentToolkit,
  vercelAiSdkAdapter,
  ChatMessagesFormatter,
} from '@tiptap-pro/extension-ai-agent-server'
import { generateText } from 'ai'
import { openai } from '@ai-sdk/openai'

const { chatMessages, schemaAwarenessData } = request

const toolkit = new AiAgentToolkit({
  adapter: vercelAiSdkAdapter,
  schemaAwarenessData,
})

const formatter = new ChatMessagesFormatter({
  // Get the chat messages from the request body
  initialMessages: chatMessages,
  adapter: vercelAiSdkAdapter,
})

// Call the Vercel AI SDK
const response = await generateText({
  model: openai('gpt-4.1'),
  messages: [
    {
      role: 'system',
      content: `
<Your system prompt>
${toolkit.getSystemPrompt()}
`,
    },
    ...formatter.format(),
  ],
  // Include the weather tool in the tools object, beside
  // the other tools provided by AiAgentToolkit
  tools: {
    ...toolkit.format(),
    get_weather: weatherTool,
  },
  // Enable multi-step tool calls
  maxSteps: 5,
})
```

Then, add the response to the formatter so that it is included in the conversation.

```ts
formatter.addAiResponse(response)
```

Finally, use the `formatter` to convert the response to the format expected by the AI Agent extension.

```ts
const response = formatter.getResolverResponse()
```

The value returned from `formatter.getResolverResponse()` should be the response of your API endpoint and the return value of the resolver function.