SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Better proposals MCP with Pydantic AI

Connect Pydantic AI to Better proposals MCP. List all proposals sent this month, create a new company profile, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Better proposals logoBetter proposals
Api Key

Better Proposals is a web-based tool for crafting and sending professional proposals. It helps teams impress clients and close deals faster with slick, easy-to-use templates.

23 Tools

Introduction

This guide walks you through connecting Better proposals to Pydantic AI using the Composio tool router. By the end, you'll have a working Better proposals agent that can track sent and signed proposals, fetch quotes and templates, create companies and proposal covers, and check your brand settings through natural language commands.

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

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

Also integrate Better proposals with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic 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 Better proposals
  • 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 Better proposals 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 Better proposals MCP server, and what's possible with it?

The Better Proposals MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Better Proposals account. It provides structured and secure access to your proposals, quotes, companies, templates, and settings, so your agent can track proposal progress, review quotes, inspect templates, create companies, and check account settings on your behalf.

  • Proposal tracking: Have your agent list proposals, count them, retrieve specific proposal details, and find proposals that are new, opened, sent, signed, or paid.
  • Quote review: Instruct your agent to list available quotes and retrieve the details of a specific quote.
  • Company management: Let the agent create new companies, list existing companies, and retrieve details about a specific company.
  • Template and document setup: Direct your agent to inspect templates and document types, create new document types, or add proposal cover designs.
  • Workspace configuration lookup: Have your agent retrieve account and brand settings, review supported currencies, and list custom merge tags.

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

Create Company

Tool to create a new company.

Create Document Type

Tool to create a new document type.

Create Proposal Cover

Tool to create a new proposal cover design.

Get All Companies

Tool to retrieve a paginated list of all companies.

Get All Currencies

Tool to retrieve a paginated list of all currencies.

Get All Document Types

Tool to retrieve a paginated list of all document types.

Get All Proposals

Tool to retrieve a paginated list of all proposals.

Get All Quotes

Tool to retrieve a paginated list of all quotes.

Get All Templates

Tool to retrieve a paginated list of all templates.

Get Brand Settings

Retrieve settings for the default brand, including its name, currency and tax configuration, for use when creating or customizing documents.

Get Company

Tool to retrieve details of a specific company.

Get Currency

Retrieve details of a specific Better Proposals currency by its ID.

Get New Proposals

Retrieve a paginated list of new proposals, optionally filtered by document type.

Get Opened Proposals

Retrieve a paginated list of proposals that recipients have opened, optionally filtered by document type.

Get Paid Proposals

Retrieve a paginated list of paid proposals, optionally filtered by document type.

Get Proposal

Retrieve details of a specific proposal by ID, including available metadata, contacts and price tables.

Get Proposal Count

Tool to retrieve the total count of proposals.

Get Quote

Tool to retrieve details of a specific quote.

Get Sent Proposals

Retrieve a page of sent proposals, optionally filtered by document type.

Get Settings

Tool to retrieve current account settings.

Get Signed Proposals

Retrieve a page of signed proposals, optionally filtered by document type.

Get Template Details

Tool to retrieve details of a specific template.

List Merge Tags

Tool to retrieve custom merge tags with pagination support.

FRAMEWORKS

How to build Better proposals MCP Agent with another framework

Claude Code logo

Claude Code

Use Better proposals MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Better proposals MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Better proposals MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Better proposals MCP with Claude Agent SDK

Codex logo

Codex

Use Better proposals MCP with Codex

OpenClaw logo

OpenClaw

Use Better proposals MCP with OpenClaw

Hermes logo

Hermes

Use Better proposals MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Better proposals MCP with Atomic Agent

Google ADK logo

Google ADK

Use Better proposals MCP with Google ADK

LangChain logo

LangChain

Use Better proposals MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Better proposals MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Better proposals MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Better proposals MCP with LlamaIndex

CrewAI logo

CrewAI

Use Better proposals MCP with CrewAI

AutoGen logo

AutoGen

Use Better proposals MCP with AutoGen

FAQ

Frequently asked questions

Start with Better proposals.It takes 30 seconds.

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

Start building