How to integrate Tave MCP with Pydantic AI

This guide walks you through connecting Tave to Pydantic AI using the Composio tool router. By the end, you'll have a working Tave agent that can list all open jobs assigned to me, add a new client to tave contacts, update status of a job to 'completed' through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Tave account through Composio's Tave MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Tave logoTave
Api Key

Tave is a studio management app for photographers, streamlining client management, job tracking, and business workflows. It helps studios stay organized and operate efficiently.

129 Tools

Introduction

This guide walks you through connecting Tave to Pydantic AI using the Composio tool router. By the end, you'll have a working Tave agent that can list all open jobs assigned to me, add a new client to tave contacts, update status of a job to 'completed' through natural language commands.

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

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

Also integrate Tave with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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

The Tave MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Tave account. It provides structured and secure access so your agent can perform Tave operations on your behalf.

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

Apply Payment to Order

Tool to apply a payment to a specific order in Tave.

Create Brand

Tool to create a new brand in VSCO Workspace.

Create Custom Field

Tool to create a custom field in Tave for Jobs or Contacts.

Create Discount Type

Tool to create a new discount type in Tave.

Create Gallery

Tool to create a new gallery in Tave (VSCO Workspace).

Create Address Book Entry

Tool to create an entry in the address book.

Create Discount

Tool to create a discount in Tave.

Create Event

Tool to create a new event in Tave (VSCO Workspace).

Create Event Type

Tool to create a new event type in Tave.

Create File

Tool to create a file in Tave.

Create Job

Tool to create a new job in Tave (VSCO Workspace).

Create Job Closed Reason

Tool to create a job closed reason in Tave.

Create Job Contact

Tool to create a job contact in Tave.

Create Job Order

Tool to create an order on a job in Tave (VSCO Workspace).

Create Job Role

Tool to create a job role in Tave (VSCO Workspace).

Create Job Type

Tool to create a new job type in Tave.

Create Job Worksheet

Tool to create a job using a worksheet in Tave (VSCO Workspace).

Create Lead Source

Tool to create a lead source in Tave.

Create Lead Status

Tool to create a lead status in Tave.

Create Note

Tool to create a note in Tave (VSCO Workspace).

Create Payment

Tool to create a payment in Tave.

Create Product

Tool to create a product in Tave.

Create Product Type

Tool to create a product type in Tave.

Create Profit Center

Tool to create a profit center in Tave.

Create RestHook Subscription

Tool to create a RestHook webhook subscription in Tave.

Create Tax Rate

Tool to create a tax rate in Tave.

Create User

Tool to create a new user in Tave.

Delete Address Book Entry

Tool to delete an entry in the address book.

Delete Brand

Tool to delete a brand by its ULID.

Delete Custom Field

Tool to delete a custom field by its ULID identifier.

Delete Event Type

Tool to delete an event type by its ULID identifier.

Delete Gallery

Tool to permanently delete a gallery by its ULID.

Delete Discount

Tool to delete a specific discount by its ULID.

Delete Discount Type

Tool to delete a specific discount type by its ULID.

Delete Event

Tool to delete an event by its ULID identifier.

Delete Job

Tool to delete a job by its ULID identifier.

Delete Job Closed Reason

Tool to delete a job closed reason by its ULID identifier.

Delete Job Contact

Tool to delete a job contact by its ULID.

Delete Job Role

Tool to delete a job role by its ULID identifier.

Delete Job Type

Tool to delete a job type by its ULID.

Delete Lead Source

Tool to delete a specific lead source by its ULID.

Delete Lead Status

Tool to delete a specific lead status by its ULID.

Delete Note

Tool to delete a note by its ULID identifier.

Delete Payment

Tool to delete a specific payment by its ULID.

Delete Product

Tool to delete a specific product by its ULID.

Delete Product Type

Tool to delete a specific product type by its ULID.

Delete Profit Center

Tool to delete a profit center by its ULID.

Delete RestHook

Tool to unsubscribe from and delete a RestHook webhook subscription by its ULID.

Delete Tax Group

Tool to delete a specific tax group by its ULID.

Delete Tax Rate

Tool to delete a specific tax rate by its ULID.

Delete User

Tool to delete a user by its ULID.

Get Brand

Tool to retrieve a specific brand from Tave by its ULID.

Get Event

Tool to get a specific event by its ID.

Get Event Type

Tool to retrieve a specific event type by ID.

Get Gallery

Tool to retrieve a specific gallery by ID from Tave/VSCO Workspace.

Get Address Book Entity

Tool to fetch a specific Address Book entity by its ULID.

Get Address Book Address

Tool to fetch the address associated with a given location ID.

Get Custom Field

Tool to fetch a specific custom field by ID from Tave.

Get Discount

Tool to retrieve a specific discount by its ID.

Get Discount Type

Tool to get a specific discount type by ID.

Get Job

Tool to fetch a specific job by ID from Tave.

Get Job Closed Reason

Tool to retrieve a specific job closed reason by its ID.

Get Job Contact

Tool to fetch a specific job contact by ID from Tave.

Get Job Role

Tool to retrieve a specific job role by its ID.

Get Job Type

Tool to retrieve a specific job type by ID.

Get Job Worksheet

Tool to fetch a Job Worksheet for a specific job by job ID.

Get Lead Source

Tool to retrieve a specific lead source by its ID.

Get Lead Status

Tool to retrieve a specific lead status by its ID.

Get My Studio

Tool to retrieve information about your studio from Tave.

Get Note

Tool to fetch a specific note by ID from Tave.

Get Order

Tool to fetch a specific order by ID from Tave.

Get Payment

Tool to fetch a specific payment by ID from Tave.

Get Payment Method

Tool to retrieve a specific payment method by its ID.

Get Product

Tool to retrieve a specific product by its ID.

Get Product Type

Tool to retrieve a specific product type by its ID.

Get Profit Center

Tool to retrieve a specific profit center by its ID.

Get Tax Rate

Tool to retrieve a specific tax rate by its ULID.

Get Timezone

Tool to retrieve a specific timezone by its ULID from Tave.

Get User by ID

Tool to retrieve a specific user by their ULID identifier.

List Address Book Contacts

Tool to list contacts in the studio's address book.

List Brands

Tool to list brands of a studio.

List Discount Types

Tool to get a list of discount types from Tave.

List Studio Events

Tool to list a studio's events from Tave.

List Event Types

Tool to list a studio's event types.

List Files

Tool to list files in Tave.

List Resource Custom Fields

Tool to list custom fields configured on a studio.

List Resource Discount

Tool to get a list of discounts from Tave.

List Galleries

Tool to list all galleries for a studio.

List Resource Job

Tool to list jobs of a studio.

List Job Closed Reasons

Tool to list a studio's job closed reasons.

List Resource Job Contact

Tool to list a job's contacts.

List Resource Job Orders

Tool to list orders on a given job.

List Job Payments

Tool to get a list of payments for a specific job.

List Job Roles

Tool to list a studio's job roles.

List Resource Job Type

Tool to list job types of a studio.

List Resource Lead Source

Tool to list lead sources of a studio.

List Resource Lead Status

Tool to list lead statuses of a studio.

List Resource Note

Tool to list notes from Tave.

List Resource Order

Tool to get a list of all orders.

List Resource Payment

Tool to get a list of payments from Tave.

List Resource Payment Method

Tool to get a list of payment methods from Tave.

List Resource Product

Tool to get a list of products from Tave.

List Product Types

Tool to get a list of product types from Tave.

List Resource Profit Center

Tool to list profit centers of a studio.

List REST Hooks

Tool to list REST hooks configured in Tave.

List Resource Tax Groups

Tool to get a list of Tax Groups from Tave.

List Resource Tax Rates

Tool to get a list of tax rates from Tave.

List Resource Timezone

Tool to get a list of timezones from Tave.

List Resource User

Tool to list users of a studio.

Update Address Book Entry

Tool to update a specific entry in the Tave address book.

Update Brand

Tool to update a specific brand in Tave.

Update Event Type

Tool to update an existing event type in Tave.

Update Custom Field

Tool to update a specific custom field in Tave.

Update Event

Tool to update a specific event in Tave.

Update Gallery

Tool to update a specific gallery in Tave (VSCO Workspace).

Update Job

Tool to update a specific job in Tave (VSCO Workspace).

Update Job Closed Reason

Tool to update a job closed reason in Tave.

Update Job Contact

Tool to update a specific job contact in Tave.

Update Job Role

Tool to update a job role in Tave.

Update Job Type

Tool to update an existing job type in Tave.

Update Lead Source

Tool to update a specific lead source in Tave.

Update Lead Status

Tool to update a specific lead status in Tave.

Update Note

Tool to update a specific note in Tave.

Update Order

Tool to update a specific order in Tave (VSCO Workspace).

Update Profit Center

Tool to update a specific profit center in Tave.

Update Tax Group

Tool to update a specific tax group in Tave.

Update Tax Rate

Tool to update a specific tax rate in Tave.

Update User

Tool to update a specific user in Tave.

Update Studio Readonly Mode

Tool to set studio readonly mode in Tave.

FRAMEWORKS

How to build Tave MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Tave MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Tave MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Tave MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Tave MCP with Claude Cowork

Codex logo

Codex

Use Tave MCP with Codex

OpenClaw logo

OpenClaw

Use Tave MCP with OpenClaw

Hermes logo

Hermes

Use Tave MCP with Hermes

CLI logo

CLI

Use Tave MCP with CLI

Google ADK logo

Google ADK

Use Tave MCP with Google ADK

LangChain logo

LangChain

Use Tave MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Tave MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Tave MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Tave MCP with LlamaIndex

CrewAI logo

CrewAI

Use Tave MCP with CrewAI

FAQ

Frequently asked questions

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

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

Start with Tave.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies