# How to integrate Smugmug MCP with Autogen ```json { "title": "How to integrate Smugmug MCP with Autogen", "toolkit": "Smugmug", "toolkit_slug": "smugmug", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/smugmug/framework/autogen", "markdown_url": "https://composio.dev/toolkits/smugmug/framework/autogen.md", "updated_at": "2026-05-12T10:26:41.033Z" } ``` ## Introduction This guide walks you through connecting Smugmug to AutoGen using the Composio tool router. By the end, you'll have a working Smugmug agent that can show all albums in your travel folder, get details for the europe 2023 album, list all child folders under weddings through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Smugmug account through Composio's Smugmug MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Smugmug with - [OpenAI Agents SDK](https://composio.dev/toolkits/smugmug/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/smugmug/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/smugmug/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/smugmug/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/smugmug/framework/codex) - [OpenClaw](https://composio.dev/toolkits/smugmug/framework/openclaw) - [Hermes](https://composio.dev/toolkits/smugmug/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/smugmug/framework/cli) - [Google ADK](https://composio.dev/toolkits/smugmug/framework/google-adk) - [LangChain](https://composio.dev/toolkits/smugmug/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/smugmug/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/smugmug/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/smugmug/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/smugmug/framework/crew-ai) ## TL;DR Here's what you'll learn: - Get and set up your OpenAI and Composio API keys - Install the required dependencies for Autogen and Composio - Initialize Composio and create a Tool Router session for Smugmug - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call Smugmug tools - Run a live chat loop where you ask the agent to perform Smugmug operations ## What is AutoGen? Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows. Key features include: - Multi-Agent Systems: Build collaborative agent workflows - MCP Workbench: Native support for Model Context Protocol tools - Streaming HTTP: Connect to external services through streamable HTTP - AssistantAgent: Pre-built agent class for tool-using assistants ## What is the Smugmug MCP server, and what's possible with it? The Smugmug MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Smugmug account. It provides structured and secure access to your photo galleries and user profile, so your agent can perform actions like browsing folders, listing albums, retrieving photo details, and exploring your Smugmug structure on your behalf. - Retrieve folder and album details: Instantly fetch information about specific folders or albums, including creation dates, node IDs, and highlight albums. - Explore your Smugmug hierarchy: Ask your agent to list all child nodes—albums or folders—within any parent node, helping you navigate your photo organization with ease. - List albums in any folder: Let your agent pull comprehensive lists of albums within a designated folder, even handling large collections with pagination. - Get public user profile info: Retrieve your Smugmug public profile details to share or review your online photography presence. - Access node-specific data: Have your agent look up details for any node (album, folder, or page) using its unique identifier, supporting granular photo management and discovery. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `SMUGMUG_GET_ALBUM` | Get Album | Retrieves detailed information about a SmugMug album using its album key. Returns album settings, metadata, image count, and links to related resources like images and user info. Use this to get comprehensive details about a specific album/gallery. | | `SMUGMUG_GET_ALBUM_HIGHLIGHT_IMAGE` | Get Album Highlight Image | Retrieves the highlight/cover image for a SmugMug album. Returns detailed information about the album's cover image including dimensions, URLs, and metadata. Use this when you need to get the featured image for an album. | | `SMUGMUG_GET_ALBUM_IMAGE` | Get Album Image | Get an image within a specific album context as an AlbumImage relationship object. Returns detailed information about the image including metadata, dimensions, URLs, and relationships. Use this when you need to retrieve a specific image from an album with full album context. | | `SMUGMUG_GET_ALBUM_IMAGES` | Get Album Images | Tool to retrieve all images in a SmugMug album as AlbumImage relationship objects. Use this action when you need to list or access images within a specific album. An AlbumImage represents the relationship between an album and an image, which is useful because the same image may appear in multiple albums. The response includes image metadata, URIs for different sizes, and pagination support for large albums. Returns AlbumImage objects with fields like ImageKey, Title, Caption, WebUri, ArchivedUri, and nested Uris for accessing related resources (ImageSizes, LargestImage, etc.). | | `SMUGMUG_GET_FOLDER_ALBUMS` | Get Folder Albums | Tool to retrieve albums from a specific folder in a SmugMug user's account by nickname and folder path. Use when you need to list albums in a folder using the user's nickname and folder path rather than NodeID. This is particularly useful when you know the folder structure but don't have the NodeID. | | `SMUGMUG_GET_FOLDER_BY_USER_PATH` | Get Folder by User and Path | Tool to retrieve folder details by user nickname and folder path. Use when you need to access a specific folder within a user's SmugMug account using the hierarchical path structure. Note: For New SmugMug, use the Node endpoint (SMUGMUG_GET_NODE_DETAILS) instead. | | `SMUGMUG_GET_FOLDER_DETAILS` | Get Folder Details | Retrieves details of a specific folder in SmugMug using its Node ID. Returns folder metadata including name, description, URL path, creation and modification dates, node ID, and optionally the URI of the album set as the highlight image for the folder. Note: This action only works with Folder-type nodes. If a non-folder node ID (e.g., Album) is provided, an error will be raised. Use SMUGMUG_GET_NODE_DETAILS for general node information. | | `SMUGMUG_GET_FOLDER_SUBFOLDERS` | Get Folder Subfolders | Retrieves all subfolders within a specified folder in a SmugMug user's account. Use this action to navigate the folder hierarchy by fetching direct child folders of a given parent folder. Specify the user's nickname and the folder path (use empty string or omit for root-level folders). Returns folder metadata including names, URLs, security settings, and IDs. | | `SMUGMUG_GET_IMAGE` | Get Image | Tool to retrieve details for a specific image (photo or video) by its image key. Returns comprehensive image metadata including dimensions, upload dates, geolocation, and links to related resources like sizes, metadata, and comments. Use when you need detailed information about a specific photo or video in SmugMug. | | `SMUGMUG_GET_IMAGE_METADATA` | Get Image Metadata | Tool to retrieve additional metadata from an image file including EXIF data, camera settings, GPS location, and other embedded information. Use when you need detailed technical information about an image, such as camera make/model, exposure settings, GPS coordinates, or timestamps. | | `SMUGMUG_GET_IMAGE_SIZE_DETAILS` | Get Image Size Details | Retrieve raw media URLs and dimensions for all available sizes of an image. Returns detailed information including direct download URLs, dimensions, and file sizes for each variant. Use this when you need to download photos or videos with specific size requirements. | | `SMUGMUG_GET_IMAGE_SIZES` | Get Image Sizes | Retrieves available image sizes and URLs for a SmugMug image by its unique image key. Use this to get download URLs for different resolutions (tiny, thumb, small, medium, large, xlarge, original, etc.). | | `SMUGMUG_GET_NODE_HIGHLIGHT_IMAGE` | Get Node Highlight Image | Tool to get the highlight/cover image for a node (folder, album, or page). Use when you need to retrieve the representative image set for a SmugMug node. | | `SMUGMUG_GET_NODE_PARENT` | Get Node Parent | Tool to retrieve the parent node of a specified SmugMug node. Use when navigating up the folder hierarchy or determining a node's location within the organizational structure. | | `SMUGMUG_GET_NODE_PARENTS` | Get Node Parents | Tool to retrieve a node and all its ancestor nodes (breadcrumb trail). Use when you need to understand the full hierarchy path from a node to the root. | | `SMUGMUG_GET_USER` | Get User | Tool to get a SmugMug user account by their nickname. Returns user details including display name, view pass hint, and links to related resources like albums, profile, and images. Use when you need to fetch basic information about a SmugMug user. | | `SMUGMUG_GET_USER_BIO_IMAGE` | Get User Bio Image | Tool to retrieve the bio image for a SmugMug user by their nickname (username). Use when you need to get information about a user's bio/profile image including image metadata, dimensions, URLs, and related resource URIs. | | `SMUGMUG_GET_USER_FEATURED_ALBUMS` | Get User Featured Albums | Retrieves the featured albums for a SmugMug user by their nickname. Use this when you need to see which albums a user has highlighted as featured content on their profile. | | `SMUGMUG_GET_USER_FEATURES` | Get User Features | Tool to retrieve a list of features available to a SmugMug user based on their subscription plan. Use when you need to check what capabilities or features a specific user has access to on SmugMug. | | `SMUGMUG_GET_USER_PROFILE` | Get User Profile | Retrieves the public profile information for a SmugMug user by their nickname (username). Returns profile details including name, bio, contact email, and social media links. Use this to get information about a SmugMug photographer or user. | | `SMUGMUG_GET_USER_ROOT_NODE` | Get User Root Node | Tool to retrieve the root node of a user's folder tree on SmugMug. Use when you need to navigate a user's gallery structure or find the starting point of their folder hierarchy. | | `SMUGMUG_LIST_CHILD_NODES` | List Child Nodes | Lists all child nodes (folders and albums) under a specified parent node in SmugMug. Use this action to navigate SmugMug's folder/album hierarchy. Start from a user's root node (obtained from user profile) and traverse down through folders to find albums. Returns child nodes with their NodeID, Type, Name, and WebUri. Use the NodeID from results to fetch further nested children or to get detailed node information. | | `SMUGMUG_SEARCH_USER_CONTENT` | Search User Content | Search for images across a user's SmugMug content. This tool searches through a user's images by querying titles, captions, keywords, and filenames. Returns a list of matching images with details like title, caption, URLs, and related resources. Use this when you need to find specific images within a user's SmugMug account. Results are returned in paginated format with up to 100 images per page. The default ordering is by popularity, but can be changed to newest or oldest. | | `SMUGMUG_UNLOCK_ALBUM` | Unlock Album | Tool to unlock a password-protected SmugMug album. Use when you need to access content in a locked album. Only available for albums that are currently password-protected. | | `SMUGMUG_UNLOCK_USER` | Unlock User Site | Tool to unlock a user's password-protected SmugMug site. Use when you need to access a locked user's site content. This action is only available if the user's site is currently locked with a password. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Smugmug MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Smugmug. Instead of manually wiring Smugmug APIs, OAuth, and scopes yourself, you get a structured, tool-based interface that an LLM can call safely. 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 You will need: - A Composio API key - An OpenAI API key (used by Autogen's OpenAIChatCompletionClient) - A Smugmug account you can connect to Composio - Some basic familiarity with Autogen and Python async ### 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 Composio, Autogen extensions, and dotenv. What's happening: - composio connects your agent to Smugmug via MCP - autogen-agentchat provides the AssistantAgent class - autogen-ext-openai provides the OpenAI model client - autogen-ext-tools provides MCP workbench support ```bash pip install composio python-dotenv pip install autogen-agentchat autogen-ext-openai autogen-ext-tools ``` ### 3. Set up environment variables Create a .env file in your project folder. What's happening: - COMPOSIO_API_KEY is required to talk to Composio - OPENAI_API_KEY is used by Autogen's OpenAI client - USER_ID is how Composio identifies which user's Smugmug connections to use ```bash COMPOSIO_API_KEY=your-composio-api-key OPENAI_API_KEY=your-openai-api-key USER_ID=your-user-identifier@example.com ``` ### 4. Import dependencies and create Tool Router session What's happening: - load_dotenv() reads your .env file - Composio(api_key=...) initializes the SDK - create(...) creates a Tool Router session that exposes Smugmug tools - session.mcp.url is the MCP endpoint that Autogen will connect to ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams load_dotenv() async def main(): # Initialize Composio and create a Smugmug session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["smugmug"] ) url = session.mcp.url ``` ### 5. Configure MCP parameters for Autogen Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for. What's happening: - url points to the Tool Router MCP endpoint from Composio - timeout is the HTTP timeout for requests - sse_read_timeout controls how long to wait when streaming responses - terminate_on_close=True cleans up the MCP server process when the workbench is closed ```python # Configure MCP server parameters for Streamable HTTP server_params = StreamableHttpServerParams( url=url, timeout=30.0, sse_read_timeout=300.0, terminate_on_close=True, headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")} ) ``` ### 6. Create the model client and agent What's happening: - OpenAIChatCompletionClient wraps the OpenAI model for Autogen - McpWorkbench connects the agent to the MCP tools - AssistantAgent is configured with the Smugmug tools from the workbench ```python # Create model client model_client = OpenAIChatCompletionClient( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY") ) # Use McpWorkbench as context manager async with McpWorkbench(server_params) as workbench: # Create Smugmug assistant agent with MCP tools agent = AssistantAgent( name="smugmug_assistant", description="An AI assistant that helps with Smugmug operations.", model_client=model_client, workbench=workbench, model_client_stream=True, max_tool_iterations=10 ) ``` ### 7. Run the interactive chat loop What's happening: - The script prompts you in a loop with You: - Autogen passes your input to the model, which decides which Smugmug tools to call via MCP - agent.run_stream(...) yields streaming messages as the agent thinks and calls tools - Typing exit, quit, or bye ends the loop ```python print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Smugmug related question or task to the agent.\n") # Conversation loop 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") # Run the agent with streaming try: response_text = "" async for message in agent.run_stream(task=user_input): if hasattr(message, "content") and message.content: response_text = message.content # Print the final response if response_text: print(f"Agent: {response_text}\n") else: print("Agent: I encountered an issue processing your request.\n") except Exception as e: print(f"Agent: Sorry, I encountered an error: {str(e)}\n") ``` ## Complete Code ```python import asyncio import os from dotenv import load_dotenv from composio import Composio from autogen_agentchat.agents import AssistantAgent from autogen_ext.models.openai import OpenAIChatCompletionClient from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams load_dotenv() async def main(): # Initialize Composio and create a Smugmug session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["smugmug"] ) url = session.mcp.url # Configure MCP server parameters for Streamable HTTP server_params = StreamableHttpServerParams( url=url, timeout=30.0, sse_read_timeout=300.0, terminate_on_close=True, headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")} ) # Create model client model_client = OpenAIChatCompletionClient( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY") ) # Use McpWorkbench as context manager async with McpWorkbench(server_params) as workbench: # Create Smugmug assistant agent with MCP tools agent = AssistantAgent( name="smugmug_assistant", description="An AI assistant that helps with Smugmug operations.", model_client=model_client, workbench=workbench, model_client_stream=True, max_tool_iterations=10 ) print("Chat started! Type 'exit' or 'quit' to end the conversation.\n") print("Ask any Smugmug related question or task to the agent.\n") # Conversation loop 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") # Run the agent with streaming try: response_text = "" async for message in agent.run_stream(task=user_input): if hasattr(message, 'content') and message.content: response_text = message.content # Print the final response if response_text: print(f"Agent: {response_text}\n") else: print("Agent: I encountered an issue processing your request.\n") except Exception as e: print(f"Agent: Sorry, I encountered an error: {str(e)}\n") if __name__ == "__main__": asyncio.run(main()) ``` ## Conclusion You now have an Autogen assistant wired into Smugmug through Composio's Tool Router and MCP. From here you can: - Add more toolkits to the toolkits list, for example notion or hubspot - Refine the agent description to point it at specific workflows - Wrap this script behind a UI, Slack bot, or internal tool Once the pattern is clear for Smugmug, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## How to build Smugmug MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/smugmug/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/smugmug/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/smugmug/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/smugmug/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/smugmug/framework/codex) - [OpenClaw](https://composio.dev/toolkits/smugmug/framework/openclaw) - [Hermes](https://composio.dev/toolkits/smugmug/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/smugmug/framework/cli) - [Google ADK](https://composio.dev/toolkits/smugmug/framework/google-adk) - [LangChain](https://composio.dev/toolkits/smugmug/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/smugmug/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/smugmug/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/smugmug/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/smugmug/framework/crew-ai) ## Related Toolkits - [Figma](https://composio.dev/toolkits/figma) - Figma is a collaborative interface design tool for teams and individuals. It streamlines design workflows with real-time collaboration and easy sharing. - [Abyssale](https://composio.dev/toolkits/abyssale) - Abyssale is a creative automation platform for generating images, videos, GIFs, PDFs, and HTML5 content programmatically. It streamlines and scales visual content production for marketing, design, and operations teams. - [Alttext ai](https://composio.dev/toolkits/alttext_ai) - AltText.ai is a service that generates alt text for images automatically. It helps boost accessibility and SEO for your visual content. - [Bannerbear](https://composio.dev/toolkits/bannerbear) - Bannerbear is an API-driven platform for generating images and videos automatically at scale. It helps businesses create custom graphics, social visuals, and marketing assets using powerful templates. - [Canva](https://composio.dev/toolkits/canva) - Canva is a drag-and-drop design suite for creating professional graphics, presentations, and marketing materials. It makes it easy for anyone to design with beautiful templates and a vast library of elements. - [Claid ai](https://composio.dev/toolkits/claid_ai) - Claid.ai delivers AI-driven image editing APIs for tasks like background removal, upscaling, and color correction. It helps automate and enhance image workflows with powerful, developer-friendly tools. - [Cloudinary](https://composio.dev/toolkits/cloudinary) - Cloudinary is a cloud-based platform for managing, uploading, and transforming images and videos. It streamlines media workflows and delivers optimized assets globally. - [Cults](https://composio.dev/toolkits/cults) - Cults is a digital marketplace for 3D printing models, connecting designers and makers. It lets creators share, sell, and discover a huge variety of printable designs easily. - [DeepImage](https://composio.dev/toolkits/deepimage) - DeepImage is an AI-powered image enhancer and upscaler. Get higher-quality images with just a few clicks. - [Dreamstudio](https://composio.dev/toolkits/dreamstudio) - DreamStudio is Stability AI’s platform for generating and editing images with AI. It lets you easily turn ideas into stunning visuals, fast. - [Dynapictures](https://composio.dev/toolkits/dynapictures) - Dynapictures is a cloud-based platform for generating personalized images at scale. Instantly create hundreds of custom visuals using your data sources, like Google Sheets. - [Fal.ai](https://composio.dev/toolkits/fal_ai) - Fal.ai is a generative media platform offering 600+ AI models for images, video, voice, and audio. Developers use Fal.ai for fast, scalable access to cutting-edge generative AI tools. - [Gamma](https://composio.dev/toolkits/gamma) - Gamma is an AI-powered platform for making beautiful, interactive presentations and documents. It lets anyone create and share engaging decks with minimal effort. - [Html to image](https://composio.dev/toolkits/html_to_image) - Html to image converts HTML and CSS into images or captures web page screenshots. Instantly generate visuals from code or web content—no manual screenshots needed. - [Imagior](https://composio.dev/toolkits/imagior) - Imagior is an AI-powered image generation platform that lets you create and customize images using dynamic templates and APIs. Perfect for businesses and creators needing fast, scalable visuals without design hassle. - [Imejis io](https://composio.dev/toolkits/imejis_io) - Imejis io is an API-based image generation platform with powerful customization and template support. It lets you create and modify images in seconds, no manual design work required. - [Imgix](https://composio.dev/toolkits/imgix) - Imgix is a real-time image processing and delivery service for developers. It helps you optimize, transform, and deliver images efficiently at any scale. - [Kraken io](https://composio.dev/toolkits/kraken_io) - Kraken.io is an image optimization and compression platform. It helps you shrink image file sizes while keeping visual quality intact. - [Logo dev](https://composio.dev/toolkits/logo_dev) - Logo.dev is an API and database for high-resolution company logos and brand metadata. Instantly fetch official logos from any domain without scraping or manual searching. - [Miro](https://composio.dev/toolkits/miro) - Miro is a collaborative online whiteboard platform for teams to brainstorm, design, and manage projects visually. It streamlines teamwork by enabling real-time idea sharing, diagramming, and workflow planning in a single space. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Smugmug MCP? With a standalone Smugmug MCP server, the agents and LLMs can only access a fixed set of Smugmug tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Smugmug and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Autogen? Yes, you can. Autogen 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 Smugmug tools. ### Can I manage the permissions and scopes for Smugmug while using Tool Router? Yes, absolutely. You can configure which Smugmug 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 Smugmug data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)