# How to integrate Lodgify MCP with Pydantic AI ```json { "title": "How to integrate Lodgify MCP with Pydantic AI", "toolkit": "Lodgify", "toolkit_slug": "lodgify", "framework": "Pydantic AI", "framework_slug": "pydantic-ai", "url": "https://composio.dev/toolkits/lodgify/framework/pydantic-ai", "markdown_url": "https://composio.dev/toolkits/lodgify/framework/pydantic-ai.md", "updated_at": "2026-05-12T10:17:54.945Z" } ``` ## Introduction This guide walks you through connecting Lodgify to Pydantic AI using the Composio tool router. By the end, you'll have a working Lodgify agent that can show available dates for property 1234, list all airbnb channel reservations this week, get all properties managed in your account through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Lodgify account through Composio's Lodgify MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Lodgify with - [OpenAI Agents SDK](https://composio.dev/toolkits/lodgify/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/lodgify/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/lodgify/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/lodgify/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/lodgify/framework/codex) - [OpenClaw](https://composio.dev/toolkits/lodgify/framework/openclaw) - [Hermes](https://composio.dev/toolkits/lodgify/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/lodgify/framework/cli) - [Google ADK](https://composio.dev/toolkits/lodgify/framework/google-adk) - [LangChain](https://composio.dev/toolkits/lodgify/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/lodgify/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/lodgify/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/lodgify/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/lodgify/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 Lodgify - 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 Lodgify 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 Lodgify MCP server, and what's possible with it? The Lodgify MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Lodgify account. It provides structured and secure access to your vacation rental properties, channels, and reservations, so your agent can perform actions like checking property availability, synchronizing channel data, retrieving reservations, and managing listings on your behalf. - Property availability checks: Instantly ask your agent to retrieve up-to-date availability information for any property, including pricing, minimum stay requirements, and current bookings. - Reservation management across channels: Let your agent list and filter reservations from all your connected channels, making it easy to track bookings and guest details in one place. - Channel synchronization and connection insights: Effortlessly pull a list of all channel connections and mappings, ensuring your property data stays in sync across platforms like Airbnb, Booking.com, and more. - Property portfolio overview: Quickly retrieve and paginate through all your properties, so you can get a comprehensive view of your listings and manage them at scale. - Supported country and channel discovery: Have your agent fetch supported countries and available channels to help with onboarding new properties or expanding your rental business. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `LODGIFY_CREATE_CALLMEBACK_REQUEST` | Create Call Me Back Request | Tool to create a Call Me Back request in Lodgify. Use when scheduling a callback appointment with a guest for property inquiries or booking assistance. | | `LODGIFY_CREATE_ENQUIRY` | Create Enquiry | Tool to create a new general enquiry with guest and reservation details. Use when a potential guest wants to make an enquiry about a property or availability. | | `LODGIFY_DECLINE_ENQUIRY` | Decline Enquiry | Tool to decline an enquiry, changing its status to Declined. Use when you need to reject or decline an enquiry from a potential guest. | | `LODGIFY_DELETE_ENQUIRY` | Delete Enquiry | Tool to delete an enquiry by moving it to the trash. Use when you need to remove an enquiry from active listings without permanently deleting it. | | `LODGIFY_DELETE_RESERVATIONS` | Delete Reservations | Tool to delete multiple bookings or enquiries in a single batch operation. Use when you need to remove several reservations at once instead of deleting them individually. | | `LODGIFY_GET_COUNTRIES` | Get Countries | Tool to retrieve all available countries. Use when you need to populate country selectors with supported ISO codes and names. | | `LODGIFY_GET_COUNTRY_BY_CODE` | Get Country by Code | Tool to retrieve a specific country by its ISO code. Use when you need to validate a country code or get the full country name for a given code. | | `LODGIFY_GET_CURRENCY_BY_CODE` | Get Currency By Code | Tool to retrieve currency details by its code. Use when you need to get information about a specific currency including its exchange rate, decimal places, and symbol. | | `LODGIFY_GET_DELETED_PROPERTIES` | Get Deleted Properties | Retrieves IDs of properties that have been deleted from the Lodgify account. Use this action to: - Get a list of all deleted property IDs - Filter deleted properties by deletion date using the deletedSince parameter - Sync local property databases by identifying which properties no longer exist Returns an array of integer property IDs. Use deletedSince to only retrieve properties deleted after a specific datetime. | | `LODGIFY_GET_EXTERNAL_BOOKINGS` | Get External Bookings | Tool to retrieve external bookings for a specific booking ID. Use when you need to get external booking details associated with a main booking record. | | `LODGIFY_GET_MESSAGING_THREAD` | Get Messaging Thread | Tool to retrieve details of a messaging thread. Use when you need to access thread information including messages, guest details, and thread status. The threadGuid parameter can be obtained from: - Reservation responses (thread_uid field) - Webhook events (guest_message_received) - Other Lodgify API endpoints that return thread identifiers | | `LODGIFY_GET_PROPERTY_AVAILABILITY` | Get Property Availability | Retrieves availability information for a specific property within a date range. This action queries the Lodgify API to get detailed availability data including: - Property ID, room type ID, and user ID - Availability periods with start and end dates - Number of units available during each period - Booking information and channel calendars - Closed period details if applicable The propertyId is required. Date range defaults to today through 30 days if not specified. Returns empty details array if no availability data exists for the property. | | `LODGIFY_GET_ROOMTYPE_AVAILABILITY` | Get Room Type Availability | Retrieves availability calendar data for a specific room type within a property for a given date range. This action queries the Lodgify API to get detailed availability information for a specific room type, including availability periods, booking status, and rates. Use when you need to check availability for a specific room type within a property, rather than for the entire property. | | `LODGIFY_GET_UNREAD_COUNT` | Get Unread Count | Retrieves the total count of unread bookings and enquiries. Use this to check how many new reservations or enquiries require attention. | | `LODGIFY_GET_V1_AVAILABILITY` | Get V1 Availability | Retrieves availability information for all properties and room types for a given date range. Use when you need to check availability across all properties in the account. Returns empty array if no availability data exists for the specified period. | | `LODGIFY_LIST_CHANNEL_CONNECTIONS` | List Channel Connections | Tool to retrieve a list of all channel connections. Use when you need to display or synchronize channel connections across properties. | | `LODGIFY_LIST_CHANNEL_MAPPINGS` | List Channel Mappings | Tool to list channel mappings. Use when you need to retrieve all channel mappings, optionally filtered by property, channel code, or external ID. Supports pagination. | | `LODGIFY_LIST_CHANNEL_RESERVATIONS` | List Channel Reservations | Tool to list channel reservations. Use when you need to retrieve reservations across channels filtered by property, channel, or date range. Results are paginated; use `limit` and `offset` together across multiple requests to retrieve all reservations, as a single request may not return the full result set. | | `LODGIFY_LIST_CHANNELS` | List Channels | Retrieves a list of all available distribution channels in the Lodgify account. Channels are booking platforms (e.g., Airbnb, Booking.com, Vrbo, Expedia) that can be connected to properties for synchronized availability and reservations. Use this action to: - Get a list of all available channels that can be connected - View channel details including ID, name, description, and active status - Check which channels are currently active in the account Returns an empty list if no channels are available or configured. | | `LODGIFY_LIST_CURRENCIES` | List Currencies | Tool to retrieve all available currency codes. Use when you need to display currency options or validate currency codes for pricing and reservations. | | `LODGIFY_LIST_PROPERTIES` | List Properties | Retrieves all properties from the Lodgify account with optional pagination. Use this action to: - Get a list of all properties in the account - Iterate through properties using pagination - Check which properties exist before performing operations on specific properties Returns property IDs, names, and address details including coordinates. Paginate through all pages until results are exhausted — stopping early silently omits remaining properties. No server-side filtering by region or location; filter client-side using returned name or address fields. | | `LODGIFY_LIST_RESERVATIONS` | List Reservations | Tool to retrieve a paginated list of bookings and enquiries from the inbox. Use when you need to fetch reservations with optional filtering by status, property, date range, or trash status. | | `LODGIFY_LIST_WEBHOOKS` | List Webhooks | Retrieves a list of all webhooks configured in the Lodgify account. Use this action to: - Get all webhook configurations - View webhook details including ID, event type, and target URL - Check which webhooks are currently set up for receiving notifications Returns an empty list if no webhooks are configured. | | `LODGIFY_MARK_RESERVATIONS_NOT_REPLIED` | Mark Reservations Not Replied | Tool to batch mark bookings and enquiries as not replied. Use when you need to mark multiple reservations (bookings or enquiries) as not replied in a single operation. | | `LODGIFY_MARK_RESERVATIONS_REPLIED` | Mark Reservations Replied | Tool to batch mark bookings or enquiries as replied. Use when you need to mark multiple reservations as replied in a single operation. | | `LODGIFY_RECOVER_ENQUIRY` | Recover Enquiry | Tool to restore an enquiry that was previously moved to the trash. Use when you need to recover a deleted enquiry by its ID. | | `LODGIFY_REOPEN_ENQUIRY` | Reopen Enquiry | Tool to reopen an enquiry, changing its status to Open. Use when you need to reactivate a previously closed or cancelled enquiry. | | `LODGIFY_SET_AVAILABILITY` | Set Availability | Updates the number of available units for a specific room type within a date range. Use this action to set availability for booking periods. The period_start and period_end dates define the range during which the specified number of units will be available. | | `LODGIFY_SUBSCRIBE_WEBHOOK` | Subscribe to Webhook | Subscribes to a Lodgify webhook by providing a target URL and event type. Use this action to: - Register a callback URL to receive real-time notifications from Lodgify - Listen for specific events like new bookings, rate changes, or availability updates - Set up integrations that respond to changes in the Lodgify system The target_url must be unique. Returns a webhook ID for later unsubscription and a secret for signature verification. | | `LODGIFY_UNSUBSCRIBE_WEBHOOK` | Unsubscribe Webhook | Tool to unsubscribe from a Lodgify webhook. Use when you need to remove a webhook subscription by providing the webhook ID that was returned during subscription. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Lodgify MCP server is an implementation of the Model Context Protocol that connects your AI agent to Lodgify. It provides structured and secure access so your agent can perform Lodgify 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 Lodgify - 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 Lodgify - MCPServerStreamableHTTP connects to the Lodgify 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 Lodgify 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 Lodgify composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["lodgify"], ) 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 Lodgify endpoint - The agent uses GPT-5 to interpret user commands and perform Lodgify operations - The instructions field defines the agent's role and behavior ```python # Attach the MCP server to a Pydantic AI Agent lodgify_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[lodgify_mcp], instructions=( "You are a Lodgify assistant. Use Lodgify 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 - Lodgify 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 Lodgify.\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 Lodgify composio = Composio(api_key=api_key) session = composio.create( user_id=user_id, toolkits=["lodgify"], ) 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 lodgify_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY}) agent = Agent( "openai:gpt-5", toolsets=[lodgify_mcp], instructions=( "You are a Lodgify assistant. Use Lodgify 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 Lodgify.\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 Lodgify through Composio's Tool Router. With this setup, your agent can perform real Lodgify 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 + Lodgify 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 Lodgify MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/lodgify/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/lodgify/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/lodgify/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/lodgify/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/lodgify/framework/codex) - [OpenClaw](https://composio.dev/toolkits/lodgify/framework/openclaw) - [Hermes](https://composio.dev/toolkits/lodgify/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/lodgify/framework/cli) - [Google ADK](https://composio.dev/toolkits/lodgify/framework/google-adk) - [LangChain](https://composio.dev/toolkits/lodgify/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/lodgify/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/lodgify/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/lodgify/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/lodgify/framework/crew-ai) ## Related Toolkits - [Google Calendar](https://composio.dev/toolkits/googlecalendar) - Google Calendar is a time management service for scheduling meetings, events, and reminders. It streamlines personal and team organization with integrated notifications and sharing options. - [Apaleo](https://composio.dev/toolkits/apaleo) - Apaleo is a cloud-based property management platform for hospitality businesses. It centralizes reservations, billing, and daily operations for smoother hotel management. - [Appointo](https://composio.dev/toolkits/appointo) - Appointo is an appointment booking platform for Shopify stores. It lets businesses add online scheduling to their websites with zero coding. - [Bart](https://composio.dev/toolkits/bart) - Bart is the Bay Area Rapid Transit system, providing fast public transportation across the San Francisco Bay Area. It helps commuters and travelers get real-time schedule info, plan routes, and stay updated on service changes. - [Bookingmood](https://composio.dev/toolkits/bookingmood) - Bookingmood is commission-free booking software for rental businesses. It lets you manage reservations and sync bookings directly on your website. - [Booqable](https://composio.dev/toolkits/booqable) - Booqable is a rental software platform for managing inventory, bookings, and reservations. It helps businesses streamline rentals and keep track of every item with ease. - [Cal](https://composio.dev/toolkits/cal) - Cal is a meeting scheduling platform that offers shareable booking links and real-time calendar syncing. It streamlines the process of finding mutual availability to make scheduling effortless. - [Calendarhero](https://composio.dev/toolkits/calendarhero) - Calendarhero is a powerful scheduling platform that streamlines your calendar management across multiple services. It helps you efficiently schedule, reschedule, and organize meetings without the back-and-forth. - [Calendly](https://composio.dev/toolkits/calendly) - Calendly is an appointment scheduling tool that automates meeting invitations, availability checks, and reminders. It helps individuals and teams avoid endless email back-and-forth when booking meetings. - [Etermin](https://composio.dev/toolkits/etermin) - eTermin is an online appointment scheduling platform for businesses to manage bookings. It streamlines client appointments, saving time and reducing scheduling conflicts. - [Evenium](https://composio.dev/toolkits/evenium) - Evenium is an all-in-one platform for managing professional events, from planning to analysis. It helps teams simplify event logistics, boost engagement, and track every detail in one place. - [Eventee](https://composio.dev/toolkits/eventee) - Eventee is a user-friendly event management platform for mobile and web. It boosts attendee engagement for in-person, virtual, and hybrid events. - [Eventzilla](https://composio.dev/toolkits/eventzilla) - Eventzilla is an event management platform for creating, promoting, and running events. It streamlines ticketing, registration, and attendee coordination for organizers. - [Humanitix](https://composio.dev/toolkits/humanitix) - Humanitix is a not-for-profit ticketing platform that donates 100% of profits to charity. It empowers event organizers to make social impact with every ticket sold. - [Planyo Online Booking](https://composio.dev/toolkits/planyo_online_booking) - Planyo Online Booking is a flexible reservation system for managing bookings by day, hour, or event. It streamlines scheduling for any business needing reservations. - [Scheduleonce](https://composio.dev/toolkits/scheduleonce) - Scheduleonce is a scheduling platform for capturing, qualifying, and engaging with inbound leads. It streamlines appointment booking and follow-ups for faster lead conversion. - [Supersaas](https://composio.dev/toolkits/supersaas) - Supersaas is a flexible appointment scheduling platform for businesses and individuals. It streamlines bookings, reminders, and calendar management in one place. - [Sympla](https://composio.dev/toolkits/sympla) - Sympla is a platform for managing in-person and online events, ticket sales, and registrations. It streamlines event setup, attendee tracking, and digital content delivery. - [Gmail](https://composio.dev/toolkits/gmail) - Gmail is Google's email service with powerful spam protection, search, and G Suite integration. It keeps your inbox organized and makes communication fast and reliable. - [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. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Lodgify MCP? With a standalone Lodgify MCP server, the agents and LLMs can only access a fixed set of Lodgify tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Lodgify 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 Lodgify tools. ### Can I manage the permissions and scopes for Lodgify while using Tool Router? Yes, absolutely. You can configure which Lodgify 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 Lodgify data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)