# How to integrate Conversion tools MCP with Pydantic AI ```json { "title": "How to integrate Conversion tools MCP with Pydantic AI", "toolkit": "Conversion tools", "toolkit_slug": "conversion_tools", "framework": "Pydantic AI", "framework_slug": "pydantic-ai", "url": "https://composio.dev/toolkits/conversion_tools/framework/pydantic-ai", "markdown_url": "https://composio.dev/toolkits/conversion_tools/framework/pydantic-ai.md", "updated_at": "2026-05-12T10:07:30.282Z" } ``` ## Introduction This guide walks you through connecting Conversion tools to Pydantic AI using the Composio tool router. By the end, you'll have a working Conversion tools agent that can convert your excel file to clean csv, export a website as a pdf snapshot, extract text from this word document through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Conversion tools account through Composio's Conversion tools MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Conversion tools with - [ChatGPT](https://composio.dev/toolkits/conversion_tools/framework/chatgpt) - [Antigravity](https://composio.dev/toolkits/conversion_tools/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/conversion_tools/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/conversion_tools/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/conversion_tools/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/conversion_tools/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/conversion_tools/framework/codex) - [Cursor](https://composio.dev/toolkits/conversion_tools/framework/cursor) - [VS Code](https://composio.dev/toolkits/conversion_tools/framework/vscode) - [OpenCode](https://composio.dev/toolkits/conversion_tools/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/conversion_tools/framework/openclaw) - [Hermes](https://composio.dev/toolkits/conversion_tools/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/conversion_tools/framework/cli) - [Google ADK](https://composio.dev/toolkits/conversion_tools/framework/google-adk) - [LangChain](https://composio.dev/toolkits/conversion_tools/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/conversion_tools/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/conversion_tools/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/conversion_tools/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/conversion_tools/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 Conversion tools - 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 Conversion tools 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 Conversion tools MCP server, and what's possible with it? The Conversion tools MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Conversion tools account. It provides structured and secure access to a wide range of file and document conversion utilities, so your agent can convert documents, extract data, generate snapshots, and automate file handling between multiple formats on your behalf. - Seamless document format conversion: Effortlessly have your agent convert Excel, Word, Markdown, OXPS, or JPG files to formats like CSV, HTML, PDF, text, or JSON. - Website snapshot creation: Ask your agent to capture entire web pages as PDF documents or PNG images, ready to download or share. - Automated file upload and processing: Let your agent upload local files, obtain conversion-ready file IDs, and initiate multi-step conversion workflows. - AI-powered data extraction: Use AI tools to transform images (JPG) into structured JSON, streamlining data entry and analysis tasks. - Easy retrieval of conversion results: Direct your agent to track conversion tasks and download the final output files once processing is complete. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `CONVERSION_TOOLS_CONVERT_EXCEL_TO_HTML` | Convert Excel to HTML | Convert an Excel (.xlsx) file to HTML table format. Use when you need to transform spreadsheet data into an HTML representation. Provide either a file upload or a public URL to the Excel file. Returns a task_id that can be used to check the conversion status and download the result once complete. | | `CONVERSION_TOOLS_CONVERT_WORD_TO_TEXT` | Convert Word to Text | Convert Word documents (.doc/.docx) to plain text (.txt). The action uploads the document, waits for conversion to complete (up to ~60 seconds), and returns the task status with a URL to download the converted text file. Use when you need to extract text content from Word documents for further processing. | | `CONVERSION_TOOLS_CREATE_TASK` | Create Conversion Task | Tool to create a new conversion task. This is the main endpoint for performing conversions across 100+ conversion types including XML, JSON, Excel, PDF, CSV, images, audio/video, and more. Use when you need to convert any supported file format or website. Counts against quota unless sandbox mode is enabled. | | `CONVERSION_TOOLS_DOWNLOAD_FILE` | Download Converted File | Download a converted file from the Conversion Tools API using its file ID. Use this action after a conversion task completes successfully. The file_id is obtained from the task status response when status is 'SUCCESS'. Converted files are automatically deleted after 24 hours. Workflow: 1. Run a conversion task (e.g., convert_website_to_pdf) 2. Check task status until status is 'SUCCESS' 3. Use the file_id from the task response to download the result | | `CONVERSION_TOOLS_GET_AUTH_INFO` | Get Auth Info | Tool to get information about the authenticated user including email address. Use when you need to verify API credentials or retrieve the user's email. | | `CONVERSION_TOOLS_GET_CONFIG` | Get Conversion Config | Tool to get available conversion types and their configuration. Returns the list of all supported conversions with their options. Use this to discover what conversions are available and what parameters they accept. | | `CONVERSION_TOOLS_GET_FILE_INFO` | Get File Info | Tool to get metadata about a file including size, name, and preview (for text files). Use when you need to retrieve information about a previously uploaded file. This does NOT count against your quota. | | `CONVERSION_TOOLS_GET_TASK_STATUS` | Get Task Status | Tool to get the status of a conversion task. Poll this endpoint until status is SUCCESS or ERROR. On SUCCESS, the response includes file_id which can be used to download the result file. | | `CONVERSION_TOOLS_LIST_TASKS` | List Conversion Tasks | Get all tasks for the authenticated user (up to 50 most recent tasks). Use this action to retrieve conversion task history, check task statuses, or find completed tasks for downloading results. This does NOT count against your API quota. Filter by status to retrieve only tasks in a specific state (PENDING, RUNNING, SUCCESS, or ERROR). | | `CONVERSION_TOOLS_UPDATE_TASK_RETENTION` | Update Task Retention | Tool to update the retention mode for a task. Use when you need to change how long task files are kept before automatic deletion. Standard mode (standard_24h) retains files for 24 hours. TTL mode (ttl_15m) is for paid users only and deletes files after 15 minutes. | | `CONVERSION_TOOLS_UPLOAD_FILE` | Upload File | Upload a file to the ConversionTools API for subsequent conversion operations. This action uploads a file and returns a file_id that can be used with other conversion actions such as convert_word_to_text, convert_excel_to_csv, convert_oxps_to_pdf, etc. Supported formats include: documents (DOC, DOCX, PDF, TXT, RTF), spreadsheets (XLS, XLSX, CSV), images (PNG, JPG, GIF, BMP), and various other file types. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Conversion tools MCP server is an implementation of the Model Context Protocol that connects your AI agent to Conversion tools. It provides structured and secure access so your agent can perform Conversion tools 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 Conversion tools - 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 Conversion tools - MCPServerStreamableHTTP connects to the Conversion tools 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 Conversion tools 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 Conversion tools composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["conversion_tools"], ) 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 Conversion tools endpoint - The agent uses GPT-5 to interpret user commands and perform Conversion tools operations - The instructions field defines the agent's role and behavior ```python # Attach the MCP server to a Pydantic AI Agent conversion_tools_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[conversion_tools_mcp], instructions=( "You are a Conversion tools assistant. Use Conversion tools 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 - Conversion tools 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 Conversion tools.\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 Conversion tools composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["conversion_tools"], ) 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 conversion_tools_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[conversion_tools_mcp], instructions=( "You are a Conversion tools assistant. Use Conversion tools 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 Conversion tools.\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 Conversion tools through Composio's Tool Router. With this setup, your agent can perform real Conversion tools 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 + Conversion tools 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 Conversion tools MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/conversion_tools/framework/chatgpt) - [Antigravity](https://composio.dev/toolkits/conversion_tools/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/conversion_tools/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/conversion_tools/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/conversion_tools/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/conversion_tools/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/conversion_tools/framework/codex) - [Cursor](https://composio.dev/toolkits/conversion_tools/framework/cursor) - [VS Code](https://composio.dev/toolkits/conversion_tools/framework/vscode) - [OpenCode](https://composio.dev/toolkits/conversion_tools/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/conversion_tools/framework/openclaw) - [Hermes](https://composio.dev/toolkits/conversion_tools/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/conversion_tools/framework/cli) - [Google ADK](https://composio.dev/toolkits/conversion_tools/framework/google-adk) - [LangChain](https://composio.dev/toolkits/conversion_tools/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/conversion_tools/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/conversion_tools/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/conversion_tools/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/conversion_tools/framework/crew-ai) ## Related Toolkits - [Google Drive](https://composio.dev/toolkits/googledrive) - Google Drive is a cloud storage platform for uploading, sharing, and collaborating on files. It's perfect for keeping your documents accessible and organized across devices. - [Google Docs](https://composio.dev/toolkits/googledocs) - Google Docs is a cloud-based word processor that enables document creation and real-time collaboration. Its seamless sharing and version history make team editing and content management a breeze. - [Google Super](https://composio.dev/toolkits/googlesuper) - Google Super is an all-in-one suite combining Gmail, Drive, Calendar, Sheets, Analytics, and more. It gives you a unified platform to manage your digital life, boosting productivity and organization. - [Affinda](https://composio.dev/toolkits/affinda) - Affinda is an AI-powered document processing platform that automates data extraction from resumes, invoices, and more. It streamlines document-heavy workflows by turning files into structured, actionable data. - [Agility cms](https://composio.dev/toolkits/agility_cms) - Agility CMS is a headless content management system for building and managing digital experiences across platforms. It lets teams update content quickly and deliver omnichannel experiences with ease. - [Algodocs](https://composio.dev/toolkits/algodocs) - Algodocs is an AI-powered platform that automates data extraction from business documents. It delivers fast, secure, and accurate processing without templates or manual training. - [Api2pdf](https://composio.dev/toolkits/api2pdf) - Api2Pdf is a REST API for generating PDFs from HTML, URLs, and documents using powerful engines like wkhtmltopdf and Headless Chrome. It streamlines document conversion and automation for developers and businesses. - [Aryn](https://composio.dev/toolkits/aryn) - Aryn is an AI-powered platform for parsing, extracting, and analyzing data from unstructured documents. Use it to automate document processing and unlock actionable insights from your files. - [Boldsign](https://composio.dev/toolkits/boldsign) - Boldsign is a digital eSignature platform for sending, signing, and tracking documents online. Organizations use it to automate agreements and manage legally binding workflows efficiently. - [Boloforms](https://composio.dev/toolkits/boloforms) - BoloForms is an eSignature platform built for small businesses, offering unlimited signatures, templates, and forms. It simplifies digital document signing and team collaboration at a predictable, fixed price. - [Box](https://composio.dev/toolkits/box) - Box is a cloud content management and file sharing platform for businesses. It helps teams securely store, organize, and collaborate on files from anywhere. - [Carbone](https://composio.dev/toolkits/carbone) - Carbone is a blazing-fast report generator that turns JSON data into PDFs, Word docs, spreadsheets, and more using flexible templates. It lets you automate document creation at scale with minimal code. - [Castingwords](https://composio.dev/toolkits/castingwords) - CastingWords is a transcription service specializing in human-powered, accurate transcripts via a simple API. Get seamless audio-to-text conversion for interviews, meetings, podcasts, and more. - [Cloudconvert](https://composio.dev/toolkits/cloudconvert) - CloudConvert is a powerful file conversion service supporting over 200 file formats. It streamlines converting, compressing, and managing documents, media, and more, all in one place. - [Cloudlayer](https://composio.dev/toolkits/cloudlayer) - Cloudlayer is a document and asset generation service for creating PDFs and images via API or SDKs. It lets you automate high-quality doc creation, saving dev time and reducing manual work. - [Cloudpress](https://composio.dev/toolkits/cloudpress) - Cloudpress is a content export tool for Google Docs and Notion. It automates publishing to your favorite Content Management Systems. - [Contentful graphql](https://composio.dev/toolkits/contentful_graphql) - Contentful graphql is a content delivery API that lets you access Contentful data using GraphQL queries. It gives you efficient, flexible ways to fetch and manage structured content for any digital project. - [Convertapi](https://composio.dev/toolkits/convertapi) - ConvertAPI is a robust file conversion service for documents, images, and spreadsheets. It streamlines programmatic format changes and lets developers automate complex workflows with a single API. - [Craftmypdf](https://composio.dev/toolkits/craftmypdf) - CraftMyPDF is a web-based service for designing and generating PDFs with templates and live data. It streamlines document creation by automating personalized PDFs at scale. - [Docmosis](https://composio.dev/toolkits/docmosis) - Docmosis generates PDF and Word documents from user-defined templates. It's perfect for merging data fields to quickly produce reports, invoices, and business letters. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Conversion tools MCP? With a standalone Conversion tools MCP server, the agents and LLMs can only access a fixed set of Conversion tools tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Conversion tools 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 Conversion tools tools. ### Can I manage the permissions and scopes for Conversion tools while using Tool Router? Yes, absolutely. You can configure which Conversion tools 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 Conversion tools 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)