How to integrate Formbricks MCP with OpenAI Agents SDK

This guide walks you through connecting Formbricks to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Formbricks agent that can create a new customer feedback survey, add a contact to our user list, record survey responses from yesterday's event through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Formbricks account through Composio's Formbricks MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Formbricks logoFormbricks
Api Key

Formbricks is an open-source platform for building and managing surveys. It helps organizations collect and analyze user feedback efficiently.

45 Tools

Introduction

This guide walks you through connecting Formbricks to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Formbricks agent that can create a new customer feedback survey, add a contact to our user list, record survey responses from yesterday's event through natural language commands.

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

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

Also integrate Formbricks 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 Formbricks
  • Configure an AI agent that can use Formbricks as a tool
  • Run a live chat session where you can ask the agent to perform Formbricks 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 Formbricks MCP server, and what's possible with it?

The Formbricks MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Formbricks account. It provides structured and secure access to your survey management tools, so your agent can perform actions like creating surveys, collecting responses, managing contacts, and handling webhooks automatically on your behalf.

  • Survey creation and management: Easily instruct your agent to create new surveys, define questions, and set up feedback forms tailored to your needs.
  • Automated response collection: Have your agent log responses to surveys, link displays to responses, and streamline data gathering effortlessly.
  • Contact and attribute management: Direct your agent to add or remove contacts, create or delete attribute classes, and segment audiences for more targeted feedback analysis.
  • Webhook configuration for real-time events: Let your agent register new webhooks to automatically send survey response data to external systems or endpoints.
  • Cleanup and maintenance tools: Authorize your agent to delete surveys, survey responses, persons, or unused attributes, keeping your Formbricks workspace organized and up to date.

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 Formbricks 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 Formbricks.
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 Formbricks
const session = await composio.create(userId as string, {
  toolkits: ['formbricks'],
});
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 formbricks.
  • The router checks the user's Formbricks connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Formbricks.
  • This approach keeps things lightweight and lets the agent request Formbricks 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 Formbricks. Help users perform Formbricks 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 Formbricks 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 Formbricks 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 Formbricks.
  • 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 Formbricks 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: ['formbricks'],
  });
  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 Formbricks. Help users perform Formbricks 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 Formbricks MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Formbricks.

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 Formbricks action and event your agent gets out of the box.

Check Health

Tool to check the health status of the Formbricks API.

Create Action Class

Tool to create a new action class.

Create Attribute Class

Creates a new attribute class (custom contact attribute) in Formbricks.

Create Client User

Tool to create or identify a user within a specified environment.

Create Contact

Creates a new contact in a Formbricks environment.

Create Display

Create a display record to track when a survey is shown to users.

Create Survey Response

Tool to create a response for a survey.

Create Survey

Tool to create a new survey.

Create Webhook

Tool to create a new webhook.

Delete Attribute Class

Tool to delete an attribute class.

Delete Person

Tool to delete a person.

Delete Survey Response

Tool to delete a survey response by its ID.

Delete Survey

Deletes a survey from Formbricks by its unique identifier.

Delete Team

Tool to delete an organization team by its ID.

Delete Webhook

Tool to delete a webhook by ID.

Get Account Info

Retrieves environment information for the authenticated API key.

Get All Contacts

Tool to retrieve all contacts within the organization.

Get Attribute Class

Tool to get a specific attribute class by ID.

Get Client Contacts State

Tool to get the current state of a contact including surveys and segment information.

Get Contact Attribute Key

Tool to retrieve detailed information about a specific contact attribute key by ID (v2 API).

Get Contact by ID

Tool to retrieve a specific contact by its ID.

Get Me

Tool to retrieve current authenticated organization's and environment details.

Get Person by ID

Tool to retrieve a person by their internal ID in Formbricks.

Get Responses

Retrieve survey responses with flexible filtering, sorting, and pagination.

Get Roles

Tool to retrieve all available roles in the system.

Get Webhook

Tool to retrieve details of a specific webhook.

List Action Classes

List all action classes in your Formbricks environment.

List Attribute Classes

Tool to list all attribute classes.

List Client Environment

Tool to retrieve environment state for Formbricks SDKs.

List Contact Attribute Keys

Tool to retrieve contact attribute keys from Formbricks.

List Health

Tool to check the health status of critical application dependencies including database and cache.

List Management Contact Attributes

Tool to retrieve all contact attributes in the environment.

List Management Me

Tool to retrieve authenticated user's environment and project information.

List Management People

Tool to retrieve all people (legacy term for contacts) in the environment.

List Organizations Project Teams

Tool to list all project-team assignments for an organization (v2 API only).

List Organization Teams

Tool to retrieve all teams in an organization (v2 API).

List Surveys

List all surveys in the environment.

List Webhooks

List all webhooks configured for the current environment.

Update Contact Attributes

Tool to update a contact's attributes in Formbricks.

Update Survey Response

Tool to update an existing survey response.

Update Survey

Updates an existing Formbricks survey with new properties.

Update Webhook

Tool to update an existing webhook.

Upload Bulk Contacts

Upload multiple contacts to a Formbricks environment in bulk (up to 250 per request).

Upload Private File

Tool to obtain S3 presigned upload data for a private survey file.

Upload Public File

Retrieves S3 presigned upload URLs and form fields for uploading a public file to Formbricks storage.

FAQ

Frequently asked questions

With a standalone Formbricks MCP server, the agents and LLMs can only access a fixed set of Formbricks tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Formbricks 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 Formbricks tools.

Yes, absolutely. You can configure which Formbricks 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 Formbricks data and credentials are handled as safely as possible.

Start with Formbricks.It takes 30 seconds.

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

Start building