How to integrate Fillout forms MCP with OpenAI Agents SDK

This guide walks you through connecting Fillout forms to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Fillout forms agent that can list all your active fillout forms, show details for your latest created form, invalidate api token for fillout account through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Fillout forms account through Composio's Fillout forms MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Fillout forms logoFillout forms
Api Key

Fillout forms is an online platform for building and managing forms with a flexible API. It lets you create, distribute, and collect responses from forms with ease.

22 Tools

Introduction

This guide walks you through connecting Fillout forms to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Fillout forms agent that can list all your active fillout forms, show details for your latest created form, invalidate api token for fillout account through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Fillout forms account through Composio's Fillout forms MCP server.

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

Also integrate Fillout forms with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Fillout forms
  • Configure an AI agent that can use Fillout forms as a tool
  • Run a live chat session where you can ask the agent to perform Fillout forms operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Fillout forms MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fillout account. It provides structured and secure access to your forms and form management tools, so your agent can fetch form data, list all your forms, manage authorization, and help automate form workflows on your behalf.

  • Comprehensive form listing: Instantly retrieve and display a list of all forms in your Fillout account, making it easy to review and manage your surveys and data collection tools.
  • Seamless authorization management: Let your agent handle the OAuth authorization flow for securely connecting third-party applications to your Fillout account—no manual steps required.
  • Token revocation and security: Instruct your agent to programmatically invalidate or revoke access tokens, ensuring that only trusted applications and users have access to your Fillout data.
  • Automated workflow integration: Use your agent to connect Fillout forms with other apps or workflows, streamlining data collection and processing without manual intervention.

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 starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Fillout forms project
  • Some knowledge of Python or Typescript
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
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Fillout forms.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Fillout forms
const session = await composio.create(userId as string, {
  toolkits: ['fillout_forms'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only fillout_forms.
  • The router checks the user's Fillout forms connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Fillout forms.
  • This approach keeps things lightweight and lets the agent request Fillout forms tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Fillout forms. Help users perform Fillout forms operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Fillout forms and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Fillout forms operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

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

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Fillout forms.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Fillout forms and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['fillout_forms'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Fillout forms. Help users perform Fillout forms operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

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

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

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

Conclusion

This was a starter code for integrating Fillout forms MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Fillout forms.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

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

Authorize OAuth

Tool to initiate the OAuth authorization process for third-party applications.

Create Database

Tool to create a new Zite database instance with tables and fields.

Create Database Webhook

Tool to create a webhook subscription for a Fillout database.

Create field

Tool to add a new field to an existing table with specified type, name, and configuration.

Create record

Tool to create a new record in a Fillout table with the provided field data.

Create table

Tool to add a new table with custom schema to an existing database.

Delete database

Tool to permanently delete a database and all its data including tables, fields, views, and records.

Delete database webhook

Tool to remove a webhook subscription from a Fillout database.

Delete field

Tool to permanently delete a field from a table.

Delete record

Tool to permanently delete a record from a table in Fillout Database.

Delete table

Tool to permanently delete a table and all its data including fields, views, and records from a Fillout database.

Get database by ID

Tool to retrieve detailed information about a specific database including all tables, fields, and views.

Get databases

Tool to retrieve a list of all databases for your organization.

Get forms

Tool to retrieve a list of all forms in your account.

Get record by ID

Tool to retrieve a single record by its UUID with all field data.

Invalidate Access Token

Revokes an OAuth access token obtained from Fillout's OAuth authorization flow.

List database webhooks

Tool to retrieve all webhook subscriptions configured for a specific database.

List Records

Tool to retrieve records from a Fillout table with filtering, sorting, and pagination.

Remove form webhook

Tool to remove a webhook by its ID.

Update field

Tool to modify field properties and configuration for an existing field in a Fillout database table.

Update record

Tool to update specific fields of an existing record in a Fillout table.

Update table

Tool to update table properties like name.

FAQ

Frequently asked questions

With a standalone Fillout forms MCP server, the agents and LLMs can only access a fixed set of Fillout forms tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Fillout forms and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Fillout forms tools.

Yes, absolutely. You can configure which Fillout forms scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Fillout forms data and credentials are handled as safely as possible.

Start with Fillout forms.It takes 30 seconds.

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

Start building