# How to integrate Fluxguard MCP with Pydantic AI ```json { "title": "How to integrate Fluxguard MCP with Pydantic AI", "toolkit": "Fluxguard", "toolkit_slug": "fluxguard", "framework": "Pydantic AI", "framework_slug": "pydantic-ai", "url": "https://composio.dev/toolkits/fluxguard/framework/pydantic-ai", "markdown_url": "https://composio.dev/toolkits/fluxguard/framework/pydantic-ai.md", "updated_at": "2026-05-12T10:11:58.419Z" } ``` ## Introduction This guide walks you through connecting Fluxguard to Pydantic AI using the Composio tool router. By the end, you'll have a working Fluxguard agent that can add competitor's homepage for daily monitoring, list all recent alerts for your sites, acknowledge today's website change alert through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Fluxguard account through Composio's Fluxguard MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Fluxguard with - [OpenAI Agents SDK](https://composio.dev/toolkits/fluxguard/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/fluxguard/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/fluxguard/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/fluxguard/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/fluxguard/framework/codex) - [OpenClaw](https://composio.dev/toolkits/fluxguard/framework/openclaw) - [Hermes](https://composio.dev/toolkits/fluxguard/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/fluxguard/framework/cli) - [Google ADK](https://composio.dev/toolkits/fluxguard/framework/google-adk) - [LangChain](https://composio.dev/toolkits/fluxguard/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/fluxguard/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/fluxguard/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/fluxguard/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/fluxguard/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 Fluxguard - 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 Fluxguard 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 Fluxguard MCP server, and what's possible with it? The Fluxguard MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Fluxguard account. It provides structured and secure access to your website monitoring and alerting data, so your agent can perform actions like adding new monitored pages, categorizing sites, retrieving alerts, acknowledging changes, and managing webhooks on your behalf. - Automated website monitoring setup: Direct your agent to add new web pages or entire sites for continuous change detection and tracking with just a quick prompt. - Alert retrieval and analysis: Have your agent fetch detailed information about recent alerts, surfacing critical changes on any monitored page instantly. - Intelligent alert acknowledgment: Let your agent acknowledge and mark alerts as reviewed, helping your team stay organized and responsive. - Site and category management: Organize your monitored properties by creating, updating, or deleting site categories to keep your web asset monitoring streamlined. - Webhook automation: Set up or remove webhooks to automate notifications, ensuring you never miss an important website change event. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `FLUXGUARD_ADD_PAGE` | Add FluxGuard Page | Tool to add a new page for monitoring in FluxGuard. This action can: 1. Create a new site with a page (when siteId/sessionId are not provided) 2. Add a page to an existing site (when siteId/sessionId are provided) When creating a new site, you can optionally assign it to categories and provide a nickname. Use this when you need to start monitoring a URL for changes. | | `FLUXGUARD_CREATE_SITE_CATEGORY` | Create FluxGuard Site Category | Creates a new site category in FluxGuard for organizing monitored websites. Site categories help you group and manage your monitored sites logically (e.g., by environment like 'Production' or 'Staging', by purpose like 'Marketing' or 'E-commerce', or by client/team). Use this action to create categories before adding sites, making it easier to filter and organize your monitoring dashboard. The returned category ID can be used when adding sites to assign them to this category. | | `FLUXGUARD_CREATE_WEBHOOK` | Create Webhook | Creates a webhook endpoint registration in FluxGuard to receive real-time notifications when changes are detected on monitored pages. When changes occur, FluxGuard will POST JSON data to your specified URL containing change details, diff information, and file references. Use this when you need to integrate FluxGuard change detection into your own systems, automation workflows, or alerting infrastructure. Note: Only one webhook can be active per account. Creating a new webhook will replace any existing webhook configuration. | | `FLUXGUARD_DELETE_PAGE` | Delete Fluxguard Page | Permanently deletes a monitored page from FluxGuard along with all its captured snapshots and version history. This is a destructive operation that cannot be undone. Use this when you need to remove a page that is no longer needed for monitoring. The operation is idempotent - deleting an already-deleted page will succeed without error. To obtain the required IDs (site_id, session_id, page_id), first use FLUXGUARD_ADD_PAGE to create a page or FLUXGUARD_GET_SITES to list existing sites and their pages. | | `FLUXGUARD_DELETE_SITE` | Delete Fluxguard Site | Permanently deletes a monitored site and all associated data including sessions, pages, and captured versions. This operation is idempotent - deleting a non-existent site returns success. Use when you need to remove a site from FluxGuard monitoring. | | `FLUXGUARD_DELETE_WEBHOOK` | Delete Webhook | Permanently removes a webhook from your FluxGuard account by its ID. After deletion, the webhook will no longer receive notifications about monitored page changes. This operation is idempotent - deleting a non-existent webhook will succeed without error. Use this tool when you need to remove a webhook configuration that is no longer needed. | | `FLUXGUARD_GET_ALL_CATEGORIES` | Get All FluxGuard Categories | Retrieves all categories defined in your FluxGuard account. Use this tool when you need to: - List all available categories for organizing sites or pages - Get category IDs for use in other operations - Check what categories exist before creating new ones This is a read-only operation that returns both site and page categories. No parameters are required - simply call this action to get all categories. | | `FLUXGUARD_GET_PAGE_DATA` | Get FluxGuard Page Data | Tool to retrieve comprehensive data for a monitored page in FluxGuard. This action fetches detailed information about a specific page including its URL, monitoring status, capture history, and metadata. Use this when you need to verify a page exists, check its monitoring status, or retrieve page configuration details. The page must be identified by its site_id, session_id, and page_id, which are typically obtained from FLUXGUARD_ADD_PAGE when creating a page or from FLUXGUARD_GET_SITES when listing existing sites and their pages. | | `FLUXGUARD_GET_SAMPLE_WEBHOOK` | Get Sample Webhook Payload | Tool to retrieve a sample webhook payload. Use when you need to inspect the structure of webhook notifications. | | `FLUXGUARD_GET_USER` | Get Current FluxGuard Account | Retrieves the authenticated FluxGuard account's information as a user profile. Returns details about the current organization's account including ID, status, creation date, and last update timestamp. This provides account information in a user-friendly format for the authenticated API key's organization. | | `FLUXGUARD_GET_WEBHOOKS` | Get FluxGuard Webhooks | Retrieves all configured webhooks for the FluxGuard account. Use this action to list all webhook endpoints that are configured to receive FluxGuard change notifications. Each webhook includes its URL, secret for signature verification, API version, and associated site categories. No parameters required - returns all webhooks for the authenticated account. | | `FLUXGUARD_INITIATE_CRAWL` | Initiate FluxGuard Crawl | Tool to initiate a crawl for a session identified by siteId and sessionId. Use when you need to start monitoring a site for changes after adding pages with FLUXGUARD_ADD_PAGE. | | `FLUXGUARD_WEBHOOK_NOTIFICATION` | Fluxguard Webhook Notification | Simulate Fluxguard webhook notification by sending change detection data to your webhook endpoint. Use this tool to test your webhook receiver implementation by sending it a properly formatted Fluxguard webhook payload with optional HMAC signature authentication. This helps verify your endpoint can receive and process Fluxguard change notifications correctly. Note: This does NOT retrieve data from Fluxguard or trigger actual monitoring - it only sends test notifications to your webhook URL. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Fluxguard MCP server is an implementation of the Model Context Protocol that connects your AI agent to Fluxguard. It provides structured and secure access so your agent can perform Fluxguard 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 Fluxguard - 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 Fluxguard - MCPServerStreamableHTTP connects to the Fluxguard 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 Fluxguard 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 Fluxguard composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["fluxguard"], ) 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 Fluxguard endpoint - The agent uses GPT-5 to interpret user commands and perform Fluxguard operations - The instructions field defines the agent's role and behavior ```python # Attach the MCP server to a Pydantic AI Agent fluxguard_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[fluxguard_mcp], instructions=( "You are a Fluxguard assistant. Use Fluxguard 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 - Fluxguard 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 Fluxguard.\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 Fluxguard composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["fluxguard"], ) 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 fluxguard_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[fluxguard_mcp], instructions=( "You are a Fluxguard assistant. Use Fluxguard 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 Fluxguard.\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 Fluxguard through Composio's Tool Router. With this setup, your agent can perform real Fluxguard 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 + Fluxguard 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 Fluxguard MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/fluxguard/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/fluxguard/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/fluxguard/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/fluxguard/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/fluxguard/framework/codex) - [OpenClaw](https://composio.dev/toolkits/fluxguard/framework/openclaw) - [Hermes](https://composio.dev/toolkits/fluxguard/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/fluxguard/framework/cli) - [Google ADK](https://composio.dev/toolkits/fluxguard/framework/google-adk) - [LangChain](https://composio.dev/toolkits/fluxguard/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/fluxguard/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/fluxguard/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/fluxguard/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/fluxguard/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 Fluxguard MCP? With a standalone Fluxguard MCP server, the agents and LLMs can only access a fixed set of Fluxguard tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Fluxguard 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 Fluxguard tools. ### Can I manage the permissions and scopes for Fluxguard while using Tool Router? Yes, absolutely. You can configure which Fluxguard 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 Fluxguard data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)