How to integrate OnlySocial MCP with Pydantic AI

This guide walks you through connecting OnlySocial to Pydantic AI using the Composio tool router. By the end, you'll have a working OnlySocial agent that can list your social accounts, review posts, upload media, create tags, and organize your tags through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a OnlySocial account through Composio's OnlySocial MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

OnlySocial logoOnlySocial
Api Key

OnlySocial is a social media management platform for workspaces, accounts, media, tags, posts, and account groups. Use it to organize and manage social publishing operations from one place.

10 Tools

Introduction

This guide walks you through connecting OnlySocial to Pydantic AI using the Composio tool router. By the end, you'll have a working OnlySocial agent that can list your social accounts, review posts, upload media, create tags, and organize your tags through natural language commands.

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

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

Also integrate OnlySocial with

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 OnlySocial
  • 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 OnlySocial 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 OnlySocial MCP server, and what's possible with it?

The OnlySocial MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your OnlySocial account. It provides structured and secure access to your connected social accounts, posts, media, and tags, so your agent can review accounts, inspect posts, manage media, and organize tags on your behalf.

  • Connected account visibility: Have your agent list connected social accounts and check their providers and authorization status.
  • Post review: Let the agent browse workspace posts and retrieve a specific post with its accounts, tags, and content versions.
  • Media library management: Direct your agent to browse images and videos, inspect file details and alt text, or upload new media for future posts.
  • Tag organization: Instruct your agent to list, create, rename, recolor, or delete tags used to organize your social content.

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 OnlySocial
  • 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 OnlySocial
  • MCPServerStreamableHTTP connects to the OnlySocial 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 OnlySocial
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["onlysocial"],
    )
    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 OnlySocial 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
onlysocial_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[onlysocial_mcp],
    instructions=(
        "You are a OnlySocial assistant. Use OnlySocial tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the OnlySocial endpoint
  • The agent uses GPT-5 to interpret user commands and perform OnlySocial 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 OnlySocial.\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
  • OnlySocial 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 OnlySocial 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 OnlySocial
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["onlysocial"],
    )
    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
    onlysocial_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[onlysocial_mcp],
        instructions=(
            "You are a OnlySocial assistant. Use OnlySocial 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 OnlySocial.\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 OnlySocial through Composio's Tool Router. With this setup, your agent can perform real OnlySocial 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 + OnlySocial 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 OnlySocial action and event your agent gets out of the box.

Create Tag

Create a named, color-coded tag in the configured OnlySocial workspace.

Delete Tag

Permanently delete one tag from the configured OnlySocial workspace.

Get Media

Get one OnlySocial media file by UUID, including its URLs, type, and alt-text metadata returned by the provider.

Get Post

Get one OnlySocial post by UUID with its accounts, tags, and content versions.

List Social Accounts

List the social accounts connected to the configured OnlySocial workspace, including provider and authorization status.

List Media

Return one page of media files from the configured OnlySocial workspace for selection when composing posts.

List Posts

Return one page of posts from the configured OnlySocial workspace.

List Tags

List all tags in the configured OnlySocial workspace for organizing or filtering posts.

Update Tag

Replace the name and color of an existing OnlySocial tag.

Upload Media

Upload an image or video file to the configured OnlySocial workspace for later use in posts.

FAQ

Frequently asked questions

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

Yes, you can. Pydantic AI 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 OnlySocial tools.

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

Start with OnlySocial.It takes 30 seconds.

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

Start building