How to integrate Formbricks MCP with OpenAI Agents SDK

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Formbricks logo
OpenAI Agents SDK logo
divider

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.

Supported Tools & Triggers

Tools
Check HealthTool to check the health status of the Formbricks API.
Create Action ClassTool to create a new action class.
Create Attribute ClassCreates a new attribute class (custom contact attribute) in Formbricks.
Create Client UserTool to create or identify a user within a specified environment.
Create ContactCreates a new contact in a Formbricks environment.
Create DisplayCreate a display record to track when a survey is shown to users.
Create Survey ResponseTool to create a response for a survey.
Create SurveyTool to create a new survey.
Create WebhookTool to create a new webhook.
Delete Attribute ClassTool to delete an attribute class.
Delete PersonTool to delete a person.
Delete Survey ResponseTool to delete a survey response by its ID.
Delete SurveyDeletes a survey from Formbricks by its unique identifier.
Delete TeamTool to delete an organization team by its ID.
Delete WebhookTool to delete a webhook by ID.
Get Account InfoRetrieves environment information for the authenticated API key.
Get All ContactsTool to retrieve all contacts within the organization.
Get Attribute ClassTool to get a specific attribute class by ID.
Get Client Contacts StateTool to get the current state of a contact including surveys and segment information.
Get Contact Attribute KeyTool to retrieve detailed information about a specific contact attribute key by ID (v2 API).
Get Contact by IDTool to retrieve a specific contact by its ID.
Get MeTool to retrieve current authenticated organization's and environment details.
Get Person by IDTool to retrieve a person by their internal ID in Formbricks.
Get ResponsesRetrieve survey responses with flexible filtering, sorting, and pagination.
Get RolesTool to retrieve all available roles in the system.
Get WebhookTool to retrieve details of a specific webhook.
List Action ClassesList all action classes in your Formbricks environment.
List Attribute ClassesTool to list all attribute classes.
List Client EnvironmentTool to retrieve environment state for Formbricks SDKs.
List Contact Attribute KeysTool to retrieve contact attribute keys from Formbricks.
List HealthTool to check the health status of critical application dependencies including database and cache.
List Management Contact AttributesTool to retrieve all contact attributes in the environment.
List Management MeTool to retrieve authenticated user's environment and project information.
List Management PeopleTool to retrieve all people (legacy term for contacts) in the environment.
List Organizations Project TeamsTool to list all project-team assignments for an organization (v2 API only).
List Organization TeamsTool to retrieve all teams in an organization (v2 API).
List SurveysList all surveys in the environment.
List WebhooksList all webhooks configured for the current environment.
Update Contact AttributesTool to update a contact's attributes in Formbricks.
Update Survey ResponseTool to update an existing survey response.
Update SurveyUpdates an existing Formbricks survey with new properties.
Update WebhookTool to update an existing webhook.
Upload Bulk ContactsUpload multiple contacts to a Formbricks environment in bulk (up to 250 per request).
Upload Private FileTool to obtain S3 presigned upload data for a private survey file.
Upload Public FileRetrieves S3 presigned upload URLs and form fields for uploading a public file to Formbricks storage.

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

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

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

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.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
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.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Formbricks Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["formbricks"]
)

mcp_url = 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.

Configure the agent

# Configure agent with MCP tool
agent = 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(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "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 dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Formbricks operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
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 Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • 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 asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["formbricks"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = 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(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

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.

How to build Formbricks MCP Agent with another framework

Claude Agent SDK logo

Claude Agent SDK

Use Formbricks MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Formbricks MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Formbricks MCP with Claude Cowork

Codex logo

Codex

Use Formbricks MCP with Codex

OpenClaw logo

OpenClaw

Use Formbricks MCP with OpenClaw

Hermes logo

Hermes

Use Formbricks MCP with Hermes

CLI logo

CLI

Use Formbricks MCP with CLI

Google ADK logo

Google ADK

Use Formbricks MCP with Google ADK

LangChain logo

LangChain

Use Formbricks MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Formbricks MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Formbricks MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Formbricks MCP with LlamaIndex

CrewAI logo

CrewAI

Use Formbricks MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Formbricks MCP?

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.

Can I use Tool Router MCP with OpenAI Agents SDK?

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.

Can I manage the permissions and scopes for Formbricks while using Tool Router?

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.

How safe is my data with Composio Tool Router?

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.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗