# How to integrate Taggun MCP with Pydantic AI ```json { "title": "How to integrate Taggun MCP with Pydantic AI", "toolkit": "Taggun", "toolkit_slug": "taggun", "framework": "Pydantic AI", "framework_slug": "pydantic-ai", "url": "https://composio.dev/toolkits/taggun/framework/pydantic-ai", "markdown_url": "https://composio.dev/toolkits/taggun/framework/pydantic-ai.md", "updated_at": "2026-05-12T10:27:48.117Z" } ``` ## Introduction This guide walks you through connecting Taggun to Pydantic AI using the Composio tool router. By the end, you'll have a working Taggun agent that can extract vendor and total from this receipt image url, list all line items from uploaded invoice link, validate this receipt url before submitting expense through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Taggun account through Composio's Taggun MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Taggun with - [OpenAI Agents SDK](https://composio.dev/toolkits/taggun/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/taggun/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/taggun/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/taggun/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/taggun/framework/codex) - [OpenClaw](https://composio.dev/toolkits/taggun/framework/openclaw) - [Hermes](https://composio.dev/toolkits/taggun/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/taggun/framework/cli) - [Google ADK](https://composio.dev/toolkits/taggun/framework/google-adk) - [LangChain](https://composio.dev/toolkits/taggun/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/taggun/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/taggun/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/taggun/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/taggun/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 Taggun - 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 Taggun 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 Taggun MCP server, and what's possible with it? The Taggun MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Taggun account. It provides structured and secure access to real-time receipt OCR and merchant management, so your agent can scan receipts, extract detailed data, validate image URLs, and manage merchant records on your behalf. - Instant receipt data extraction: Have your agent process receipt or invoice images via public URLs to pull out structured purchase data quickly and accurately. - Detailed line item analysis: Use verbose extraction to get comprehensive data including line items, merchant info, and confidence metrics from receipt images or PDFs. - Automated merchant registry management: Export the full list of known merchants for audits or synchronize merchant data directly through your agent. - Receipt image URL validation: Let your agent check if a receipt image URL meets campaign and validation requirements before processing. - Generate merchant mock CSVs for testing: Easily create sample merchant CSV files to test or bulk import merchant data as part of your automation workflow. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `TAGGUN_ADD_MERCHANT_NAME` | Add Merchant Name | Tool to add a merchant name keyword to your account's model for predicting merchant names. Use when you want to improve merchant name recognition by training the model with specific merchant names. Changes to your account's model are updated daily and will affect future receipt processing. | | `TAGGUN_EXPORT_KNOWN_MERCHANTS` | Export Known Merchants | Export the complete list of known merchants used for merchant name normalization in Taggun. Returns CSV data with merchant details including location IDs, names, addresses, and coordinates. Use this when you need to retrieve the full merchant registry for synchronization, auditing, or analysis. No parameters required - this is a read-only GET operation. | | `TAGGUN_EXPORT_KNOWN_PRODUCT_CODES` | Export Known Product Codes | Export the complete list of known product codes used for product normalization and matching in Taggun. Returns CSV data with product code information. Use this when you need to retrieve the full product code registry for synchronization, auditing, or analysis. No parameters required - this is a read-only GET operation. | | `TAGGUN_EXPORT_PRODUCT_CATEGORIES` | Export Product Categories | Export a list of product categories and descriptions used for product categorization in CSV format. Returns CSV data with product category information for analysis or synchronization purposes. Use this when you need to retrieve the complete product category registry. | | `TAGGUN_GENERATE_MERCHANTS_CSV` | Generate Merchants CSV | Generate a CSV file with mock merchant data for testing purposes. Creates a temporary CSV file with the specified number of merchant rows, including fields like name, alias, address, coordinates, contact info, and tags. Use this when you need sample merchant data for bulk import operations or testing merchant-related API endpoints. The generated CSV follows a standard format with 10 columns: name, alias, address, postcode, lat, lng, country, phone, email, tags. | | `TAGGUN_IMPORT_KNOWN_MERCHANTS` | Import Known Merchants | Import a list of merchant names and addresses to normalize and match in CSV or TSV format. Use this when you need to bulk upload merchant data for name normalization and matching. File must be less than 20MB and contain merchant information in CSV or TSV format. | | `TAGGUN_IMPORT_KNOWN_PRODUCT_CODES` | Import Known Product Codes | Tool to import a list of product codes in CSV or TSV format for normalization and matching. Use when you need to upload product code data to Taggun for receipt/invoice processing. The file should contain product codes with descriptions (e.g., code,description columns). | | `TAGGUN_IMPORT_PRODUCT_CATEGORIES` | Import Product Categories | Import a list of product categories and descriptions for product categorization. Accepts CSV or TSV files (less than 20MB) with category and description columns. Use this when you need to bulk import product category data for matching during receipt processing. | | `TAGGUN_TRANSCRIBE_RECEIPT_ENCODED_SIMPLE` | Transcribe Receipt from Base64 Encoded Image | Extract structured data from a receipt or invoice using base64 encoded image data. Provide a base64 encoded image (JPEG, PNG, PDF, GIF) along with filename and content type to get back extracted fields like total amount, date, merchant name, tax, line items, and confidence scores. Use this when you have receipt/invoice image data already encoded as base64 and need to digitize the data. The API uses machine learning OCR to detect and extract key fields automatically. | | `TAGGUN_TRANSCRIBE_RECEIPT_ENCODED_VERBOSE` | Transcribe Receipt Encoded Verbose | Tool to transcribe a receipt using base64 encoded image in JSON payload and return detailed results. Use when you have a base64 encoded receipt image and require comprehensive output including line items, merchant details, and confidence levels. The image must be larger than 1x1 pixels to avoid validation errors. | | `TAGGUN_TRANSCRIBE_RECEIPT_FILE_SIMPLE` | Transcribe Receipt File (Simple) | Tool to upload a receipt or invoice image file and extract basic data including merchant name, total amount, tax amount, and date. Use when you need to digitize receipt data from a file (PDF, JPG, PNG, GIF, HEIC up to 20MB). The API uses OCR to detect and extract key fields. | | `TAGGUN_URL` | Process Receipt via URL | Extract structured data from a receipt or invoice image using OCR. Provide a public URL to a receipt/invoice image (JPEG, PNG, PDF, GIF) and get back extracted fields like total amount, date, merchant name, tax, line items, and confidence scores. Use this when you need to digitize receipt/invoice data from a publicly accessible image URL. The API uses machine learning OCR to detect and extract key fields automatically. | | `TAGGUN_URL_VALIDATION` | URL Validation | Tool to extract and validate receipt data from a URL. Processes a receipt image from a public URL and returns extracted fields with confidence levels to assess receipt authenticity. Use when you have a receipt URL and need to verify it contains valid receipt data. | | `TAGGUN_URL_VERBOSE` | URL Verbose | Tool to process a receipt or invoice from a URL for detailed data extraction. Use when you have a publicly accessible receipt or invoice URL and require comprehensive output including line items, merchant details, and confidence metrics. Call after verifying the URL is reachable. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Taggun MCP server is an implementation of the Model Context Protocol that connects your AI agent to Taggun. It provides structured and secure access so your agent can perform Taggun 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 Taggun - 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 Taggun - MCPServerStreamableHTTP connects to the Taggun 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 Taggun 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 Taggun composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["taggun"], ) 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 Taggun endpoint - The agent uses GPT-5 to interpret user commands and perform Taggun operations - The instructions field defines the agent's role and behavior ```python # Attach the MCP server to a Pydantic AI Agent taggun_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[taggun_mcp], instructions=( "You are a Taggun assistant. Use Taggun 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 - Taggun 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 Taggun.\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 Taggun composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["taggun"], ) 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 taggun_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[taggun_mcp], instructions=( "You are a Taggun assistant. Use Taggun 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 Taggun.\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 Taggun through Composio's Tool Router. With this setup, your agent can perform real Taggun 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 + Taggun 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 Taggun MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/taggun/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/taggun/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/taggun/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/taggun/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/taggun/framework/codex) - [OpenClaw](https://composio.dev/toolkits/taggun/framework/openclaw) - [Hermes](https://composio.dev/toolkits/taggun/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/taggun/framework/cli) - [Google ADK](https://composio.dev/toolkits/taggun/framework/google-adk) - [LangChain](https://composio.dev/toolkits/taggun/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/taggun/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/taggun/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/taggun/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/taggun/framework/crew-ai) ## Related Toolkits - [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management. - [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters. - [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions. - [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows. - [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations. - [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements. - [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints. - [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots. - [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches. - [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand. - [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance. - [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows. - [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses. - [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research. - [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction. - [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation. - [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation. - [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Taggun MCP? With a standalone Taggun MCP server, the agents and LLMs can only access a fixed set of Taggun tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Taggun 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 Taggun tools. ### Can I manage the permissions and scopes for Taggun while using Tool Router? Yes, absolutely. You can configure which Taggun 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 Taggun data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)