SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Customgpt MCP with Pydantic AI

Connect Pydantic AI to Customgpt MCP. List all your active customgpt projects, show chat history from your latest conversation, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Customgpt logoCustomgpt
Api Key

CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code.

40 Tools

Introduction

This guide walks you through connecting Customgpt to Pydantic AI using the Composio tool router. By the end, you'll have a working Customgpt agent that can create and update agent projects, add data sources, start conversations, review conversation analytics, and verify answer accuracy through natural language commands.

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

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

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Customgpt with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Customgpt
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Customgpt workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

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

The Customgpt MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your CustomGPT.ai account. It provides structured and secure access to your chatbot projects, so your agent can list, manage, update, and analyze your AI-powered chatbots and their licenses on your behalf.

  • Project and agent management: Effortlessly list all your CustomGPT projects, retrieve their details, and even delete agents you no longer need.
  • Comprehensive license handling: Let your agent fetch, update, or remove licenses attached to any of your chatbot projects, ensuring you always have the right access and compliance.
  • Chat conversation insights: Retrieve complete chat histories from your AI chatbot conversations to analyze user interactions or debug sessions.
  • User profile and usage monitoring: Automatically fetch your account profile and check on your usage limits, including agents, words, and queries, so you never exceed your quotas.
  • Project settings inspection: Quickly pull and review configuration details for any chatbot project to audit or adjust your bot's setup.

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:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
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 dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Customgpt
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Customgpt
  • MCPServerStreamableHTTP connects to the Customgpt MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Customgpt
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["customgpt"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Customgpt tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
customgpt_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[customgpt_mcp],
    instructions=(
        "You are a Customgpt assistant. Use Customgpt tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Customgpt endpoint
  • The agent uses GPT-5 to interpret user commands and perform Customgpt operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Customgpt.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Customgpt API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Customgpt and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Customgpt
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["customgpt"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    customgpt_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[customgpt_mcp],
        instructions=(
            "You are a Customgpt assistant. Use Customgpt tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Customgpt.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Customgpt through Composio's Tool Router. With this setup, your agent can perform real Customgpt actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Customgpt for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

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

Activate Persona Version

Restore a previous persona version for a CustomGPT agent.

Add Source to Project

Add a data source to a CustomGPT agent's knowledge base using a sitemap URL or file upload.

Clone CustomGPT Project

Tool to clone a CustomGPT agent (project).

Create Conversation

Tool to create a new conversation session for a CustomGPT agent.

Create CustomGPT Project

Create a new CustomGPT agent from either a sitemap URL or a file upload.

Delete Page from Agent

Tool to delete a document from a CustomGPT agent's knowledge base.

Delete CustomGPT Project

Tool to delete a CustomGPT project by ID.

Delete CustomGPT Project License

Delete a license from a CustomGPT project or agent using its numeric project ID and license ID.

Delete CustomGPT Source

Tool to delete a data source from a CustomGPT agent.

Export Leads

Export leads from a CustomGPT project.

Get Message

Tool to get message details from a CustomGPT conversation.

Get Message Trust Score

Retrieves verification trust assessment data for a message in a CustomGPT conversation.

Get Page Metadata

Tool to get document metadata including title, source URL, word count, and custom metadata fields.

Get Agent Plugins

Retrieves plugin details for a specific CustomGPT agent, including configuration, status, and metadata.

Get CustomGPT Project

Get details for a specific CustomGPT agent, including its status and metadata such as ownership, sharing, sitemap, and embed information.

Get Project License

Retrieve a license for a specific CustomGPT project by license ID.

Get Project Settings

Retrieves configuration settings for a CustomGPT agent, including avatar, background, prompt, language, and branding preferences.

Get Analytics Chart Data

Tool to retrieve analytics chart data for a CustomGPT project.

Get Conversation Analytics

Tool to get conversation analytics for a CustomGPT project.

Get Customer Intelligence Report

Tool to get customer intelligence for a CustomGPT project.

Get Traffic Analytics Report

Tool to retrieve traffic analytics for a CustomGPT agent/project.

Get Agent Statistics

Get usage and document statistics for a CustomGPT agent, including query counts, credits used, and pages found, crawled, and indexed.

Get Usage Limits

Get account usage and limits for projects, storage credits, and API queries.

Get Current User Profile

Tool to retrieve the current user's profile information.

List Conversation Messages

Retrieve messages from a CustomGPT conversation, including user queries and AI responses.

List Agent Documents

Lists documents in a CustomGPT agent's knowledge base, including webpages and uploaded files.

List Persona Versions

Tool to list persona versions for a CustomGPT agent.

List CustomGPT Project Licenses

List licenses for a CustomGPT project or agent using its numeric project ID.

List CustomGPT Projects

Lists all CustomGPT projects (agents) for the authenticated user.

List Agent Sources

Tool to list all data sources connected to an agent.

Reindex Page

Starts reindexing a URL-based document in a CustomGPT knowledge base to update its content.

Search Team Members

Tool to search for team members by email address or user ID.

Submit Message Feedback

Tool to submit feedback (thumbs up/down) for a message in a CustomGPT conversation.

Update Page Metadata

Updates metadata for a specific page in a CustomGPT project, including its title, description, URL, and image.

Update Project

Updates an existing CustomGPT agent's name or project configuration, including sharing, sitemap, license, and document-processing settings.

Update Project License

Updates the name of an existing license for a CustomGPT project/agent.

Update Project Settings

Update CustomGPT agent configuration settings.

Update Source Settings

Update settings for a CustomGPT agent data source, including auto-sync frequency, refresh behavior, JavaScript execution, image extraction, page creation and removal, and custom refresh schedules.

Update User Profile

Updates the authenticated user's profile information in CustomGPT.

Verify Message Accuracy

Trigger verification of a message in a CustomGPT conversation.

FRAMEWORKS

How to build Customgpt MCP Agent with another framework

Claude Code logo

Claude Code

Use Customgpt MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Customgpt MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Customgpt MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Customgpt MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Customgpt MCP with Grok Bot

Codex logo

Codex

Use Customgpt MCP with Codex

OpenClaw logo

OpenClaw

Use Customgpt MCP with OpenClaw

Hermes logo

Hermes

Use Customgpt MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Customgpt MCP with Atomic Agent

Google ADK logo

Google ADK

Use Customgpt MCP with Google ADK

LangChain logo

LangChain

Use Customgpt MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Customgpt MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Customgpt MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Customgpt MCP with LlamaIndex

CrewAI logo

CrewAI

Use Customgpt MCP with CrewAI

AutoGen logo

AutoGen

Use Customgpt MCP with AutoGen

FAQ

Frequently asked questions

Start with Customgpt.It takes 30 seconds.

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

Start building