SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Airtable MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Airtable MCP. Add new contacts from a signup list, create a project tracking table in workspace, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Airtable logoAirtable
Oauth2Api Key

Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.

26 Tools6 Triggers

Introduction

This guide walks you through connecting Airtable to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Airtable agent that can create and update records, build bases and tables, manage fields, add comments, and upload attachments through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Airtable account through Composio's Airtable MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Airtable with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Airtable integration
  • Using Composio's Tool Router to dynamically load and access Airtable tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

What is the Airtable MCP server, and what's possible with it?

The Airtable MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Airtable account. It provides structured and secure access to your bases, table structures, records, and account details, so your agent can inspect bases, retrieve records, create entries, and update data on your behalf.

  • Base discovery: Have your agent list the Airtable bases available to your connected account.
  • Table and field inspection: Let the agent review a base’s tables, fields, field types, and configurations before working with its data.
  • Record retrieval: Direct your agent to fetch a specific record when you need its latest field values.
  • Natural language record creation: Instruct your agent to turn a plain-language request into a new Airtable record or create several records at once.
  • Targeted record updates: Have your agent modify selected fields in one or several existing records while preserving the remaining data.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["airtable"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Airtable tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Airtable-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Airtable tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to airtable, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Airtable tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Airtable and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["airtable"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to airtable, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Airtable agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS & TRIGGERS

Supported Tools and Triggers

Every Airtable action and event your agent gets out of the box.

Create base

Creates a new Airtable base with specified tables and fields within a workspace.

Create Comment

Tool to create a comment on a specific Airtable record.

Create Field

Creates a new field within a specified table in an Airtable base.

Create Record From Natural Language

Creates an Airtable record from a natural language description using the table schema and an LLM-generated field payload.

Create records

Tool to create multiple records (up to 10) in a specified Airtable table.

Create table

Creates a table in an existing Airtable base with a specified name, description, and field structure.

Delete Comment

Tool to delete a comment from a record in an Airtable table.

Delete multiple records

Tool to delete up to 10 specified records from a table within an Airtable base.

Delete Record

Permanently deletes a specific record from an existing table within an existing Airtable base.

Get Attachment Info

Retrieves attachment metadata and download URLs from a specified Airtable record field, including sizes, types, and thumbnails when available; attachment URLs expire 2 hours after retrieval.

Get Base Metadata

Retrieves basic metadata for one Airtable base.

Get Base Schema

Retrieves the detailed schema for a specified Airtable base, including its tables, fields, field types, and configurations, using the `baseId`.

Get Record

Retrieves a specific record from an Airtable table by its record ID.

Get user information

Retrieves information, such as ID and permission scopes, for the currently authenticated Airtable user from the `/meta/whoami` endpoint.

List bases

Lists a page of Airtable bases accessible to the authenticated token.

List Comments

Tool to list comments on a specific Airtable record.

List records

Tool to list records from an Airtable table with filtering, sorting, and pagination.

Update Comment

Tool to update an existing comment on a specific Airtable record.

Update Field

Updates a field's name or description in an Airtable table.

Update multiple records

Tool to update up to 10 records in an Airtable table with selective field modifications.

Update multiple records (PUT)

Tool to destructively update multiple records in Airtable using PUT, clearing unspecified fields.

Update record

Modifies specified fields of an existing record in an Airtable base and table; the base, table, and record must exist.

Update record (PUT)

Updates an existing record in an Airtable base using PUT method.

Update Table

Updates the name, description, and/or date dependency settings of a table in Airtable.

Upload attachment

Uploads a file attachment to a specified field in an Airtable record.

Who Am I

Returns the connected Airtable account's user ID and, when available, email address.

FRAMEWORKS

How to build Airtable MCP Agent with another framework

Claude Code logo

Claude Code

Use Airtable MCP with Claude Code

Cursor logo

Cursor

Use Airtable MCP with Cursor

ChatGPT logo

ChatGPT

Use Airtable MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Airtable MCP with Claude Cowork

Antigravity logo

Antigravity

Use Airtable MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Airtable MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Airtable MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Airtable MCP with Grok Bot

Muse logo

Muse

Use Airtable MCP with Muse

Codex logo

Codex

Use Airtable MCP with Codex

Grok Build logo

Grok Build

Use Airtable MCP with Grok Build

VS Code logo

VS Code

Use Airtable MCP with VS Code

OpenCode logo

OpenCode

Use Airtable MCP with OpenCode

OpenClaw logo

OpenClaw

Use Airtable MCP with OpenClaw

Hermes logo

Hermes

Use Airtable MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Airtable MCP with Atomic Agent

Google ADK logo

Google ADK

Use Airtable MCP with Google ADK

LangChain logo

LangChain

Use Airtable MCP with LangChain

Mastra AI logo

Mastra AI

Use Airtable MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Airtable MCP with LlamaIndex

CrewAI logo

CrewAI

Use Airtable MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Airtable MCP with Pydantic AI

AutoGen logo

AutoGen

Use Airtable MCP with AutoGen

FAQ

Frequently asked questions

Start with Airtable.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Airtable tool your agent needs.Free to start.

Start building