# How to integrate Poof MCP with Pydantic AI ```json { "title": "How to integrate Poof MCP with Pydantic AI", "toolkit": "Poof", "toolkit_slug": "poof", "framework": "Pydantic AI", "framework_slug": "pydantic-ai", "url": "https://composio.dev/toolkits/poof/framework/pydantic-ai", "markdown_url": "https://composio.dev/toolkits/poof/framework/pydantic-ai.md", "updated_at": "2026-03-29T06:46:08.933Z" } ``` ## Introduction This guide walks you through connecting Poof to Pydantic AI using the Composio tool router. By the end, you'll have a working Poof agent that can send crypto payment to a vendor, check status of latest poof transaction, generate invoice for client in usd through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Poof account through Composio's Poof MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Poof with - [OpenAI Agents SDK](https://composio.dev/toolkits/poof/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/poof/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/poof/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/poof/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/poof/framework/codex) - [OpenClaw](https://composio.dev/toolkits/poof/framework/openclaw) - [Hermes](https://composio.dev/toolkits/poof/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/poof/framework/cli) - [Google ADK](https://composio.dev/toolkits/poof/framework/google-adk) - [LangChain](https://composio.dev/toolkits/poof/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/poof/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/poof/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/poof/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/poof/framework/crew-ai) ## 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 Poof - 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 Poof 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 Poof MCP server, and what's possible with it? The Poof MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Poof account. It provides structured and secure access so your agent can perform Poof operations on your behalf. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `POOF_CHECK_BALANCE` | Check Balance | Tool to check the balance of a cryptocurrency wallet. Use when you need to retrieve the current balance for a specified blockchain wallet address. | | `POOF_CREATE_CHECKOUT` | Create Checkout Session | Tool to create a checkout session for fiat payments. Use when you need to generate a payment link for customers to complete their purchase through the Poof payment infrastructure. | | `POOF_CREATE_DEPOSIT_ADDRESS` | Create Deposit Address | Tool to create a deposit address for receiving cryptocurrency payments. Generates a unique blockchain address to accept incoming crypto deposits. Use when you need to create a payment address for a customer to send cryptocurrency to. | | `POOF_CREATE_FIAT_CHARGE` | Create Fiat Charge | Tool to create a fiat currency charge through Poof's payment gateway integration. Use when initiating a one-time fiat payment collection via PayPal, Stripe, Square, or other supported gateways. | | `POOF_CREATE_FIAT_INVOICE` | Create Fiat Invoice | Create a fiat currency invoice for payment collection. Generates an invoice for collecting payments in traditional currencies via payment processors like PayPal, Stripe, Square, Cash App, etc. Returns a checkout URL for customer payment. | | `POOF_CREATE_PAYMENT_LINK` | Create Payment Link | Tool to create a payment link (invoice) for cryptocurrency payments. Use when you need to generate a shareable payment URL for collecting crypto payments from customers. | | `POOF_CREATE_POOF_WEBHOOK` | Create Poof Webhook | Tool to create a webhook subscription for receiving payment event notifications. Use when you need to set up real-time notifications for transaction status changes and other payment events. | | `POOF_FETCH_GAS_PRICE` | Fetch Gas Price | Tool to fetch current gas prices for blockchain transactions. Returns gas price estimates for Ethereum, Avalanche, Polygon, and other supported EVM chains across different priority levels (slow, standard, fast, instant). | | `POOF_FETCH_CRYPTOCURRENCY_PRICE` | Fetch Cryptocurrency Price | Tool to fetch current cryptocurrency prices for supported tokens. Use when you need real-time price data for cryptocurrencies and tokens. | | `POOF_FETCH_SMART_CONTRACTS` | Fetch Smart Contracts | Tool to fetch all supported ERC-20 smart contracts across Ethereum, Avalanche, and Polygon networks. Use when you need to retrieve available token contracts and their details for blockchain operations. | | `POOF_SEND_CRYPTOCURRENCY_PAYOUT` | Send Cryptocurrency Payout | Tool to send a cryptocurrency payout transaction from your wallet to an external address. Use when you need to transfer crypto on supported blockchains. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Poof MCP server is an implementation of the Model Context Protocol that connects your AI agent to Poof. It provides structured and secure access so your agent can perform Poof operations on your behalf through a secure, permission-based interface. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 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 ### 1. Getting API Keys for OpenAI and Composio OpenAI API Key - Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) 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](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install dependencies Install the required libraries. What's happening: - composio connects your agent to external SaaS tools like Poof - pydantic-ai lets you create structured AI agents with tool support - python-dotenv loads your environment variables securely from a .env file ```bash pip install composio pydantic-ai python-dotenv ``` ### 3. Set up environment variables 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 ```bash COMPOSIO_API_KEY=your_composio_api_key_here USER_ID=your_user_id_here OPENAI_API_KEY=your_openai_api_key ``` ### 4. Import dependencies What's happening: - We load environment variables and import required modules - Composio manages connections to Poof - MCPServerStreamableHTTP connects to the Poof MCP server endpoint - Agent from Pydantic AI lets you define and run the AI assistant ```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() ``` ### 5. Create a Tool Router Session What's happening: - We're creating a Tool Router session that gives your agent access to Poof 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 ```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 Poof composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["poof"], ) url = session.mcp.url if not url: raise ValueError("Composio session did not return an MCP URL") ``` ### 6. Initialize the Pydantic AI Agent What's happening: - The MCP client connects to the Poof endpoint - The agent uses GPT-5 to interpret user commands and perform Poof operations - The instructions field defines the agent's role and behavior ```python # Attach the MCP server to a Pydantic AI Agent poof_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[poof_mcp], instructions=( "You are a Poof assistant. Use Poof tools to help users " "with their requests. Ask clarifying questions when needed." ), ) ``` ### 7. Build the chat interface What's happening: - The agent reads input from the terminal and streams its response - Poof API calls happen automatically under the hood - The model keeps conversation history to maintain context across turns ```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 Poof.\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() ``` ### 8. Run the application What's happening: - The asyncio loop launches the agent and keeps it running until you exit ```python if __name__ == "__main__": asyncio.run(main()) ``` ## Complete Code ```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 Poof composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["poof"], ) 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 poof_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[poof_mcp], instructions=( "You are a Poof assistant. Use Poof 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 Poof.\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 Poof through Composio's Tool Router. With this setup, your agent can perform real Poof 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 + Poof for workflow automation) This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations. ## How to build Poof MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/poof/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/poof/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/poof/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/poof/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/poof/framework/codex) - [OpenClaw](https://composio.dev/toolkits/poof/framework/openclaw) - [Hermes](https://composio.dev/toolkits/poof/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/poof/framework/cli) - [Google ADK](https://composio.dev/toolkits/poof/framework/google-adk) - [LangChain](https://composio.dev/toolkits/poof/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/poof/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/poof/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/poof/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/poof/framework/crew-ai) ## Related Toolkits - [Stripe](https://composio.dev/toolkits/stripe) - Stripe is a global online payments platform offering APIs for managing payments, customers, and subscriptions. Trusted by businesses for secure, efficient, and scalable payment processing worldwide. - [Addresszen](https://composio.dev/toolkits/addresszen) - Addresszen is a real-time address autocomplete and verification service. It helps capture accurate, deliverable addresses with instant suggestions and validation. - [Alpha vantage](https://composio.dev/toolkits/alpha_vantage) - Alpha Vantage is a financial data platform offering real-time and historical stock market APIs. Get instant, reliable access to equities, forex, and technical analysis data for smarter trading decisions. - [Altoviz](https://composio.dev/toolkits/altoviz) - Altoviz is a cloud-based billing and invoicing platform for businesses. It streamlines online payments, expense tracking, and customizable invoice management. - [Asin data api](https://composio.dev/toolkits/asin_data_api) - Asin data api gives you detailed, real-time product data from Amazon, including price, rank, and reviews. Perfect for e-commerce pros and data-driven marketers who need instant marketplace insights. - [Baselinker](https://composio.dev/toolkits/baselinker) - BaseLinker is an all-in-one e-commerce management platform connecting stores, marketplaces, carriers, and more. It streamlines order processing, inventory control, and automates your sales operations. - [Benzinga](https://composio.dev/toolkits/benzinga) - Benzinga provides real-time financial news and data APIs for market coverage. It helps you track breaking news and actionable market insights instantly. - [Bestbuy](https://composio.dev/toolkits/bestbuy) - Best Buy is a leading retailer offering APIs for product, store, and recommendation data. Instantly access up-to-date retail insights for smarter shopping and decision-making. - [Brex](https://composio.dev/toolkits/brex) - Brex provides corporate credit cards and spend management tailored for startups and tech businesses. It helps optimize company cash flow, streamline accounting, and accelerate business growth. - [Btcpay server](https://composio.dev/toolkits/btcpay_server) - BTCPay Server is a free, open-source, self-hosted Bitcoin payment processor. It lets merchants accept Bitcoin payments directly, cutting out middlemen and boosting privacy. - [Cdr platform](https://composio.dev/toolkits/cdr_platform) - Cdr platform is an API for purchasing carbon dioxide removal services. It enables businesses to offset emissions by accessing verified carbon removal projects. - [Chaser](https://composio.dev/toolkits/chaser) - Chaser is accounts receivable automation software that sends invoice reminders and helps businesses get paid faster. It streamlines the collections process to save time and improve cash flow. - [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time. - [Cloudcart](https://composio.dev/toolkits/cloudcart) - CloudCart is an e-commerce platform for building and managing online stores. It helps businesses streamline product listings, orders, and customer engagement. - [Coinbase](https://composio.dev/toolkits/coinbase) - Coinbase is a platform for buying, selling, and storing cryptocurrency. It makes exchanging and managing crypto simple and secure for everyone. - [Coinranking](https://composio.dev/toolkits/coinranking) - Coinranking is a comprehensive cryptocurrency market data platform offering access to real-time coin prices, market caps, and historical data. Get accurate, up-to-date stats for thousands of digital assets in one place. - [Countdown api](https://composio.dev/toolkits/countdown_api) - Countdown API gives you real-time, structured eBay product data, reviews, and seller feedback. Perfect for powering price monitoring, product research, or marketplace analytics workflows. - [Coupa](https://composio.dev/toolkits/coupa) - Coupa is a business spend management platform for procurement, invoicing, and expenses. It helps organizations streamline purchasing, control costs, and gain complete visibility over financial operations. - [CurrencyScoop](https://composio.dev/toolkits/currencyscoop) - CurrencyScoop is a developer-friendly API for real-time and historical currency exchange rates. Easily access fiat and crypto data for smart, up-to-date financial applications. - [Daffy](https://composio.dev/toolkits/daffy) - Daffy is a modern charitable giving platform with a donor-advised fund. Easily set aside funds, grow them tax-free, and donate to over 1.7 million U.S. charities. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Poof MCP? With a standalone Poof MCP server, the agents and LLMs can only access a fixed set of Poof tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Poof and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Pydantic AI? 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 Poof tools. ### Can I manage the permissions and scopes for Poof while using Tool Router? Yes, absolutely. You can configure which Poof 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 Poof data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) ยท [Composio docs](https://docs.composio.dev/llms.txt)