How to integrate Formdesk MCP with OpenAI Agents SDK

Framework Integration Gradient
Formdesk Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Formdesk to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Formdesk agent that can add a new field to my registration form, submit a new entry to feedback form 12345, delete the email field from survey form 67890, get details of entry id 555 in form 4321 through natural language commands.

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

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

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 Formdesk
  • Configure an AI agent that can use Formdesk as a tool
  • Run a live chat session where you can ask the agent to perform Formdesk operations

What is open-ai-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 Formdesk MCP server, and what's possible with it?

The Formdesk MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Formdesk account. It provides structured and secure access to your online forms, so your agent can perform actions like submitting entries, managing form fields, handling visitors, and retrieving detailed information on your behalf.

  • Automated form entry submission: Let your agent instantly submit new responses to any of your Formdesk forms using collected or generated data.
  • Dynamic form structure management: Easily create new fields or delete existing ones, allowing your agent to adapt forms as your requirements change.
  • Detailed entry and field retrieval: Have your agent fetch comprehensive details about specific form entries or fields for auditing, review, or analysis.
  • Visitor management automation: Add or remove visitors in your forms, streamlining registration and access workflows with AI assistance.
  • Effortless form and data cleanup: Direct your agent to delete forms, entries, fields, or visitors, keeping your Formdesk workspace organized and up to date.

Supported Tools & Triggers

Tools
Automatic LoginTool to perform automatic login to Formdesk and retrieve an access token.
Create Formdesk EntryTool to submit a new entry to a Formdesk form.
Create FieldTool to create a new field in a specific Formdesk form.
Create VisitorTool to add a new visitor to a specific Formdesk form.
Delete Formdesk EntryTool to delete a specific entry from a Formdesk form.
Delete Field in FormdeskTool to delete a specific field in a Formdesk form.
Delete Form in FormdeskTool to delete a specific form.
Delete Visitor in FormdeskTool to delete a specific visitor in a Formdesk form.
Get Entry DetailsTool to retrieve detailed information about a specific Formdesk entry.
Get Field DetailsTool to retrieve detailed information about a specific field.
Get Form DetailsTool to retrieve detailed information about a specific Formdesk form.
Get Form EntriesTool to retrieve all entries for a specified Formdesk form.
Get Form FieldsTool to retrieve all fields of a specific form.
Get Form ListTool to retrieve a list of all forms available in the account.
Get Form VisitorsTool to retrieve all visitors for a specified Formdesk form.
Get Visitor DetailsTool to retrieve detailed information about a specific Formdesk visitor.
KVK Handelsregister LookupTool to lookup company details from the Dutch KVK Handelsregister.
Manage Visitor EntriesTool to list or retrieve a visitor's own form entries.
Create Multi-Page FormTool to create a multi-page Formdesk form.
Prepopulate Formdesk FieldsTool to prepopulate form fields.
Update FieldTool to update an existing field definition on a Formdesk form.
Update FormTool to update an existing form.
Update VisitorTool to update an existing visitor for a given form.
Webhook IntegrationTool to send form submission data to external webhooks.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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 Formdesk 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 Formdesk.

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 Formdesk Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["formdesk"]
)

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 formdesk.
  • The router checks the user's Formdesk connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Formdesk.
  • This approach keeps things lightweight and lets the agent request Formdesk 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 Formdesk. "
        "Help users perform Formdesk 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 Formdesk 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 Formdesk 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 Formdesk.
  • 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 Formdesk and open-ai-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=["formdesk"]
)
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 Formdesk. "
        "Help users perform Formdesk 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 Formdesk MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Formdesk.

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 Formdesk MCP Agent with another framework

FAQ

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

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

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

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

Used by agents from

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