# How to integrate Replicate MCP with Pydantic AI ```json { "title": "How to integrate Replicate MCP with Pydantic AI", "toolkit": "Replicate", "toolkit_slug": "replicate", "framework": "Pydantic AI", "framework_slug": "pydantic-ai", "url": "https://composio.dev/toolkits/replicate/framework/pydantic-ai", "markdown_url": "https://composio.dev/toolkits/replicate/framework/pydantic-ai.md", "updated_at": "2026-05-12T10:23:52.496Z" } ``` ## Introduction This guide walks you through connecting Replicate to Pydantic AI using the Composio tool router. By the end, you'll have a working Replicate agent that can run stable diffusion to generate an image, list all your uploaded files on replicate, get readme documentation for a model through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Replicate account through Composio's Replicate MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Replicate with - [ChatGPT](https://composio.dev/toolkits/replicate/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/replicate/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/replicate/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/replicate/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/replicate/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/replicate/framework/codex) - [Cursor](https://composio.dev/toolkits/replicate/framework/cursor) - [VS Code](https://composio.dev/toolkits/replicate/framework/vscode) - [OpenCode](https://composio.dev/toolkits/replicate/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/replicate/framework/openclaw) - [Hermes](https://composio.dev/toolkits/replicate/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/replicate/framework/cli) - [Google ADK](https://composio.dev/toolkits/replicate/framework/google-adk) - [LangChain](https://composio.dev/toolkits/replicate/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/replicate/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/replicate/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/replicate/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/replicate/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 Replicate - 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 Replicate 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 Replicate MCP server, and what's possible with it? The Replicate MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Replicate account. It provides structured and secure access to your Replicate resources, so your agent can perform actions like running AI model predictions, managing files, browsing model collections, and retrieving model documentation on your behalf. - Run and manage AI model predictions: Easily instruct your agent to create, monitor, and manage predictions on any deployed Replicate model using custom input parameters. - Browse and discover model collections: Ask your agent to fetch and list available model collections or retrieve example predictions to explore what’s possible on Replicate. - Upload and organize files: Let your agent upload new files, list all stored files, or inspect file details to streamline your model workflows. - Access model metadata and documentation: Retrieve full model details, schemas, and markdown README docs for any model to help you choose and utilize the right model for your tasks. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `REPLICATE_ACCOUNT_GET` | Get Account Information | Tool to get authenticated account information. Use when you need to retrieve details about the account associated with the API token. | | `REPLICATE_CANCEL_PREDICTION` | Cancel Prediction | Tool to cancel a prediction that is still running. Use when you need to stop an in-progress prediction to free up resources or halt execution. | | `REPLICATE_COLLECTIONS_GET` | Get model collection | Tool to get a specific collection of models by its slug. Use when you need detailed information about a collection and its models. | | `REPLICATE_COLLECTIONS_LIST` | List model collections | Tool to list all collections of models. Use when you need to retrieve available model collections. Collections are curated groupings of related models. Response includes only collection metadata (name, slug, description), not individual models within each collection; use REPLICATE_MODELS_GET for per-model details. Response may include a non-null `next` field indicating additional pages; follow it to enumerate all collections. | | `REPLICATE_CREATE_MODEL` | Create Model | Tool to create a new Replicate model with specified owner, name, visibility, and hardware. Use when you need to create a destination model before launching LoRA/fine-tune training. | | `REPLICATE_CREATE_PREDICTION` | Create Prediction | Tool to create a prediction for a Replicate Deployment. IMPORTANT: This action ONLY works with Replicate Deployments (persistent instances you create and manage), NOT public models. Deployments are created via REPLICATE_DEPLOYMENTS_CREATE. To run public models (e.g., 'meta/llama-2-70b-chat', 'stability-ai/sdxl'), use REPLICATE_MODELS_PREDICTIONS_CREATE instead. Use 'wait_for' to wait until the prediction completes. | | `REPLICATE_DEPLOYMENTS_CREATE` | Create Deployment | Tool to create a new deployment with specified model, version, hardware, and scaling parameters. Use when you need to deploy a model for production use with auto-scaling. | | `REPLICATE_DEPLOYMENTS_DELETE` | Delete Deployment | Tool to delete a deployment from your account. Use when you need to remove a deployment. Deployments must be offline and unused for at least 15 minutes before deletion. | | `REPLICATE_DEPLOYMENTS_GET` | Get Deployment Details | Tool to get deployment details by owner and name. Use when you need information about a specific deployment including its release configuration and hardware settings. | | `REPLICATE_DEPLOYMENTS_LIST` | List deployments | Tool to list all deployments associated with the account. Use when you need to retrieve deployment configurations and their latest releases. | | `REPLICATE_CREATE_FILE` | Create File | Tool to create or upload a file to Replicate. Use when you need to upload file content with optional metadata. | | `REPLICATE_FILES_DELETE` | Delete File | Tool to delete a file by its ID. Use when you need to remove a file from storage. Returns 204 No Content on success. | | `REPLICATE_FILES_GET` | Get File Details | Tool to get details of a file by its ID. Use when you need to inspect uploaded file information before further operations. Returned URLs may be short-lived; download or persist needed files promptly after retrieval. | | `REPLICATE_FILES_LIST` | List Files | Tool to retrieve a paginated list of uploaded files. Use to view all files created by the authenticated user or organization. Files are sorted with most recent first. Pagination is cursor-based: follow the next cursor until empty to retrieve all files. Limit requests to 1–2/second to avoid 429 Too Many Requests errors. Use to validate current file_ids before passing to prediction tools, as stale file_ids cause runtime errors. | | `REPLICATE_GET_PREDICTION` | Get Prediction | Tool to get the status and output of a prediction by its ID. Use when you need to check on a running prediction or retrieve the results of a completed prediction. | | `REPLICATE_HARDWARE_LIST` | List Available Hardware | Tool to list available hardware SKUs for models and deployments. Use when you need to see what hardware options are available on the Replicate platform. | | `REPLICATE_MODELS_EXAMPLES_LIST` | List model examples | Tool to list example predictions for a specific model. Use when you want to retrieve author-provided illustrative examples after identifying the model. Returned examples are minimal working payloads; cross-reference with REPLICATE_MODELS_README_GET before calling REPLICATE_CREATE_PREDICTION to satisfy strict input validation. | | `REPLICATE_MODELS_GET` | Get Model Details | Tool to get details of a specific model by owner and name. Consult the returned input schema before constructing any prediction request — each model defines its own required/optional fields (e.g., `prompt`, `aspect_ratio`, `version`); missing or unknown keys cause validation errors. Model schemas and available versions may change over time; recheck before production use. | | `REPLICATE_MODELS_LIST` | List Public Models | Tool to list public models with pagination and sorting. Use when you need to browse available models or find models sorted by creation date. | | `REPLICATE_MODELS_PREDICTIONS_CREATE` | Create Model Prediction | Tool to create a prediction using an official Replicate model. Use when you need to run inference with a specific model using its owner and name. Supports synchronous waiting (up to 60 seconds) and webhooks for async notifications. | | `REPLICATE_MODELS_README_GET` | Get Model README | Tool to get the README content for a model in Markdown format. Consult alongside REPLICATE_MODELS_EXAMPLES_LIST before calling REPLICATE_CREATE_PREDICTION — Replicate enforces strict JSON schemas on model inputs and returns 422 errors for incorrect keys or types. Use after retrieving model details when you want to view its documentation. | | `REPLICATE_MODELS_VERSIONS_GET` | Get Model Version | Tool to get a specific version of a model. Use when you need details about a particular model version including its schema and metadata. | | `REPLICATE_MODELS_VERSIONS_LIST` | List Model Versions | Tool to list all versions of a specific model. Use when you need to see all available versions of a model, sorted by newest first. | | `REPLICATE_CREATE_PREDICTION` | Create Prediction | Tool to create a prediction to run a model by version ID. Use when you have a specific model version identifier and need to run inference with provided inputs. Supports synchronous waiting and webhook notifications. | | `REPLICATE_PREDICTIONS_LIST` | List All Predictions | Tool to list all predictions for the authenticated user or organization with pagination. Use when you need to retrieve prediction history or filter predictions by creation date. | | `REPLICATE_SEARCH` | Search Models and Collections | Tool to search for models, collections, and docs using text queries (beta). Use when you need to find relevant models or collections based on keywords or descriptions. | | `REPLICATE_TRAININGS_CANCEL` | Cancel Training | Tool to cancel an ongoing training operation in Replicate. Use when you need to stop a training job that is in progress. | | `REPLICATE_TRAININGS_CREATE` | Create Training Job | Tool to create a training job for a specific model version. Use when you need to fine-tune a model with custom training data. Supports webhook notifications for training status updates. | | `REPLICATE_TRAININGS_LIST` | List Training Jobs | Tool to list all training jobs for the authenticated user or organization with pagination. Use when you need to retrieve training history or check the status of training jobs. | | `REPLICATE_UPDATE_MODELS` | Update Model Metadata | Tool to update metadata for a model including description, URLs, and README. Use when you need to modify a model's visibility, documentation, or associated links. | | `REPLICATE_WEBHOOKS_SECRET_GET` | Get Webhook Signing Secret | Tool to get the signing secret for the default webhook. Use when you need to retrieve the secret key used to verify webhook authenticity. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Replicate MCP server is an implementation of the Model Context Protocol that connects your AI agent to Replicate. It provides structured and secure access so your agent can perform Replicate 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 Replicate - 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 Replicate - MCPServerStreamableHTTP connects to the Replicate 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 Replicate 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 Replicate composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["replicate"], ) 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 Replicate endpoint - The agent uses GPT-5 to interpret user commands and perform Replicate operations - The instructions field defines the agent's role and behavior ```python # Attach the MCP server to a Pydantic AI Agent replicate_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[replicate_mcp], instructions=( "You are a Replicate assistant. Use Replicate 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 - Replicate 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 Replicate.\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 Replicate composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["replicate"], ) 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 replicate_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[replicate_mcp], instructions=( "You are a Replicate assistant. Use Replicate 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 Replicate.\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 Replicate through Composio's Tool Router. With this setup, your agent can perform real Replicate 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 + Replicate 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 Replicate MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/replicate/framework/chatgpt) - [OpenAI Agents SDK](https://composio.dev/toolkits/replicate/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/replicate/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/replicate/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/replicate/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/replicate/framework/codex) - [Cursor](https://composio.dev/toolkits/replicate/framework/cursor) - [VS Code](https://composio.dev/toolkits/replicate/framework/vscode) - [OpenCode](https://composio.dev/toolkits/replicate/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/replicate/framework/openclaw) - [Hermes](https://composio.dev/toolkits/replicate/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/replicate/framework/cli) - [Google ADK](https://composio.dev/toolkits/replicate/framework/google-adk) - [LangChain](https://composio.dev/toolkits/replicate/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/replicate/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/replicate/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/replicate/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/replicate/framework/crew-ai) ## Related Toolkits - [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed. - [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service. - [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows. - [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow. - [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows. - [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application. - [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities. - [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization. - [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications. - [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations. - [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key. - [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient. - [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions. - [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences. - [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement. - [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team. - [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs. - [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code. - [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets. - [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Replicate MCP? With a standalone Replicate MCP server, the agents and LLMs can only access a fixed set of Replicate tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Replicate 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 Replicate tools. ### Can I manage the permissions and scopes for Replicate while using Tool Router? Yes, absolutely. You can configure which Replicate 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 Replicate data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)