# How to integrate Smugmug MCP with LlamaIndex ```json { "title": "How to integrate Smugmug MCP with LlamaIndex", "toolkit": "Smugmug", "toolkit_slug": "smugmug", "framework": "LlamaIndex", "framework_slug": "llama-index", "url": "https://composio.dev/toolkits/smugmug/framework/llama-index", "markdown_url": "https://composio.dev/toolkits/smugmug/framework/llama-index.md", "updated_at": "2026-05-12T10:26:41.033Z" } ``` ## Introduction This guide walks you through connecting Smugmug to LlamaIndex 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 LlamaIndex 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) - [CrewAI](https://composio.dev/toolkits/smugmug/framework/crew-ai) ## TL;DR Here's what you'll learn: - Set your OpenAI and Composio API keys - Install LlamaIndex and Composio packages - Create a Composio Tool Router session for Smugmug - Connect LlamaIndex to the Smugmug MCP server - Build a Smugmug-powered agent using LlamaIndex - Interact with Smugmug through natural language ## What is LlamaIndex? LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools. Key features include: - ReAct Agent: Reasoning and acting pattern for tool-using agents - MCP Tools: Native support for Model Context Protocol - Context Management: Maintain conversation context across interactions - Async Support: Built for async/await patterns ## 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 agent to Smugmug. It provides structured and secure access so your agent can perform Smugmug 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 you begin, make sure you have: - Python 3.8/Node 16 or higher installed - A Composio account with the API key - An OpenAI API key - A Smugmug account and project - Basic familiarity with async Python/Typescript ### 1. Getting API Keys for OpenAI, Composio, and Smugmug No description provided. ### 2. Installing dependencies No description provided. ```python pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv ``` ```typescript npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv ``` ### 3. Set environment variables Create a .env file in your project root: These credentials will be used to: - Authenticate with OpenAI's GPT-5 model - Connect to Composio's Tool Router - Identify your Composio user session for Smugmug access ```bash OPENAI_API_KEY=your-openai-api-key COMPOSIO_API_KEY=your-composio-api-key COMPOSIO_USER_ID=your-user-id ``` ### 4. Import modules No description provided. ```python import asyncio import os import dotenv from composio import Composio from composio_llamaindex import LlamaIndexProvider from llama_index.core.agent.workflow import ReActAgent from llama_index.core.workflow import Context from llama_index.llms.openai import OpenAI from llama_index.tools.mcp import BasicMCPClient, McpToolSpec dotenv.load_dotenv() ``` ```typescript import "dotenv/config"; import readline from "node:readline/promises"; import { stdin as input, stdout as output } from "node:process"; import { Composio } from "@composio/core"; import { mcp } from "@llamaindex/tools"; import { agent as createAgent } from "@llamaindex/workflow"; import { openai } from "@llamaindex/openai"; dotenv.config(); ``` ### 5. Load environment variables and initialize Composio No description provided. ```python OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not OPENAI_API_KEY: raise ValueError("OPENAI_API_KEY is not set in the environment") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set in the environment") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set in the environment") ``` ```typescript const OPENAI_API_KEY = process.env.OPENAI_API_KEY; const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY; const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID; if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set"); if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set"); if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set"); ``` ### 6. Create a Tool Router session and build the agent function What's happening here: - We create a Composio client using your API key and configure it with the LlamaIndex provider - We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, smugmug) - The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools - LlamaIndex will connect to this endpoint to dynamically discover and use the available Smugmug tools. - The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent. ```python async def build_agent() -> ReActAgent: composio_client = Composio( api_key=COMPOSIO_API_KEY, provider=LlamaIndexProvider(), ) session = composio_client.create( user_id=COMPOSIO_USER_ID, toolkits=["smugmug"], ) mcp_url = session.mcp.url print(f"Composio MCP URL: {mcp_url}") mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY}) mcp_tool_spec = McpToolSpec(client=mcp_client) tools = await mcp_tool_spec.to_tool_list_async() llm = OpenAI(model="gpt-5") description = "An agent that uses Composio Tool Router MCP tools to perform Smugmug actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Smugmug actions. """ return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True) ``` ```typescript async function buildAgent() { console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`); console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`); const composio = new Composio({ apiKey: COMPOSIO_API_KEY, provider: new LlamaindexProvider(), }); const session = await composio.create( COMPOSIO_USER_ID!, { toolkits: ["smugmug"], }, ); const mcpUrl = session.mcp.url; console.log(`Composio Tool Router MCP URL: ${mcpUrl}`); const server = mcp({ url: mcpUrl, clientName: "composio_tool_router_with_llamaindex", requestInit: { headers: { "x-api-key": COMPOSIO_API_KEY!, }, }, // verbose: true, }); const tools = await server.tools(); const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" }); const agent = createAgent({ name: "composio_tool_router_with_llamaindex", description : "An agent that uses Composio Tool Router MCP tools to perform actions.", systemPrompt: "You are a helpful assistant connected to Composio Tool Router."+ "Use the available tools to answer user queries and perform Smugmug actions." , llm, tools, }); return agent; } ``` ### 7. Create an interactive chat loop No description provided. ```python async def chat_loop(agent: ReActAgent) -> None: ctx = Context(agent) print("Type 'quit', 'exit', or Ctrl+C to stop.") while True: try: user_input = input("\nYou: ").strip() except (KeyboardInterrupt, EOFError): print("\nBye!") break if not user_input or user_input.lower() in {"quit", "exit"}: print("Bye!") break try: print("Agent: ", end="", flush=True) handler = agent.run(user_input, ctx=ctx) async for event in handler.stream_events(): # Stream token-by-token from LLM responses if hasattr(event, "delta") and event.delta: print(event.delta, end="", flush=True) # Show tool calls as they happen elif hasattr(event, "tool_name"): print(f"\n[Using tool: {event.tool_name}]", flush=True) # Get final response response = await handler print() # Newline after streaming except KeyboardInterrupt: print("\n[Interrupted]") continue except Exception as e: print(f"\nError: {e}") ``` ```typescript async function chatLoop(agent: ReturnType) { const rl = readline.createInterface({ input, output }); console.log("Type 'quit' or 'exit' to stop."); while (true) { let userInput: string; try { userInput = (await rl.question("\nYou: ")).trim(); } catch { console.log("\nAgent: Bye!"); break; } if (!userInput) { continue; } const lower = userInput.toLowerCase(); if (lower === "quit" || lower === "exit") { console.log("Agent: Bye!"); break; } try { process.stdout.write("Agent: "); const stream = agent.runStream(userInput); let finalResult: any = null; for await (const event of stream) { // The event.data contains the streamed content const data: any = event.data; // Check for streaming delta content if (data?.delta) { process.stdout.write(data.delta); } // Store final result for fallback if (data?.result || data?.message) { finalResult = data; } } // If no streaming happened, show the final result if (finalResult) { const answer = finalResult.result ?? finalResult.message?.content ?? finalResult.message ?? ""; if (answer && typeof answer === "string" && !answer.includes("[object")) { process.stdout.write(answer); } } console.log(); // New line after streaming completes } catch (err: any) { console.error("\nAgent error:", err?.message ?? err); } } rl.close(); } ``` ### 8. Define the main entry point What's happening here: - We're orchestrating the entire application flow - The agent gets built with proper error handling - Then we kick off the interactive chat loop so you can start talking to Smugmug ```python async def main() -> None: agent = await build_agent() await chat_loop(agent) if __name__ == "__main__": # Handle Ctrl+C gracefully signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0))) try: asyncio.run(main()) except KeyboardInterrupt: print("\nBye!") ``` ```typescript async function main() { try { const agent = await buildAgent(); await chatLoop(agent); } catch (err) { console.error("Failed to start agent:", err); process.exit(1); } } main(); ``` ### 9. Run the agent When prompted, authenticate and authorise your agent with Smugmug, then start asking questions. ```bash python llamaindex_agent.py ``` ```typescript npx ts-node llamaindex-agent.ts ``` ## Complete Code ```python import asyncio import os import signal import dotenv from composio import Composio from composio_llamaindex import LlamaIndexProvider from llama_index.core.agent.workflow import ReActAgent from llama_index.core.workflow import Context from llama_index.llms.openai import OpenAI from llama_index.tools.mcp import BasicMCPClient, McpToolSpec dotenv.load_dotenv() OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not OPENAI_API_KEY: raise ValueError("OPENAI_API_KEY is not set") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set") async def build_agent() -> ReActAgent: composio_client = Composio( api_key=COMPOSIO_API_KEY, provider=LlamaIndexProvider(), ) session = composio_client.create( user_id=COMPOSIO_USER_ID, toolkits=["smugmug"], ) mcp_url = session.mcp.url print(f"Composio MCP URL: {mcp_url}") mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY}) mcp_tool_spec = McpToolSpec(client=mcp_client) tools = await mcp_tool_spec.to_tool_list_async() llm = OpenAI(model="gpt-5") description = "An agent that uses Composio Tool Router MCP tools to perform Smugmug actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Smugmug actions. """ return ReActAgent( tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True, ); async def chat_loop(agent: ReActAgent) -> None: ctx = Context(agent) print("Type 'quit', 'exit', or Ctrl+C to stop.") while True: try: user_input = input("\nYou: ").strip() except (KeyboardInterrupt, EOFError): print("\nBye!") break if not user_input or user_input.lower() in {"quit", "exit"}: print("Bye!") break try: print("Agent: ", end="", flush=True) handler = agent.run(user_input, ctx=ctx) async for event in handler.stream_events(): # Stream token-by-token from LLM responses if hasattr(event, "delta") and event.delta: print(event.delta, end="", flush=True) # Show tool calls as they happen elif hasattr(event, "tool_name"): print(f"\n[Using tool: {event.tool_name}]", flush=True) # Get final response response = await handler print() # Newline after streaming except KeyboardInterrupt: print("\n[Interrupted]") continue except Exception as e: print(f"\nError: {e}") async def main() -> None: agent = await build_agent() await chat_loop(agent) if __name__ == "__main__": # Handle Ctrl+C gracefully signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0))) try: asyncio.run(main()) except KeyboardInterrupt: print("\nBye!") ``` ```typescript import "dotenv/config"; import readline from "node:readline/promises"; import { stdin as input, stdout as output } from "node:process"; import { Composio } from "@composio/core"; import { LlamaindexProvider } from "@composio/llamaindex"; import { mcp } from "@llamaindex/tools"; import { agent as createAgent } from "@llamaindex/workflow"; import { openai } from "@llamaindex/openai"; dotenv.config(); const OPENAI_API_KEY = process.env.OPENAI_API_KEY; const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY; const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID; if (!OPENAI_API_KEY) { throw new Error("OPENAI_API_KEY is not set in the environment"); } if (!COMPOSIO_API_KEY) { throw new Error("COMPOSIO_API_KEY is not set in the environment"); } if (!COMPOSIO_USER_ID) { throw new Error("COMPOSIO_USER_ID is not set in the environment"); } async function buildAgent() { console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`); console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`); const composio = new Composio({ apiKey: COMPOSIO_API_KEY, provider: new LlamaindexProvider(), }); const session = await composio.create( COMPOSIO_USER_ID!, { toolkits: ["smugmug"], }, ); const mcpUrl = session.mcp.url; console.log(`Composio Tool Router MCP URL: ${mcpUrl}`); const server = mcp({ url: mcpUrl, clientName: "composio_tool_router_with_llamaindex", requestInit: { headers: { "x-api-key": COMPOSIO_API_KEY!, }, }, // verbose: true, }); const tools = await server.tools(); const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" }); const agent = createAgent({ name: "composio_tool_router_with_llamaindex", description: "An agent that uses Composio Tool Router MCP tools to perform actions.", systemPrompt: "You are a helpful assistant connected to Composio Tool Router."+ "Use the available tools to answer user queries and perform Smugmug actions." , llm, tools, }); return agent; } async function chatLoop(agent: ReturnType) { const rl = readline.createInterface({ input, output }); console.log("Type 'quit' or 'exit' to stop."); while (true) { let userInput: string; try { userInput = (await rl.question("\nYou: ")).trim(); } catch { console.log("\nAgent: Bye!"); break; } if (!userInput) { continue; } const lower = userInput.toLowerCase(); if (lower === "quit" || lower === "exit") { console.log("Agent: Bye!"); break; } try { process.stdout.write("Agent: "); const stream = agent.runStream(userInput); let finalResult: any = null; for await (const event of stream) { // The event.data contains the streamed content const data: any = event.data; // Check for streaming delta content if (data?.delta) { process.stdout.write(data.delta); } // Store final result for fallback if (data?.result || data?.message) { finalResult = data; } } // If no streaming happened, show the final result if (finalResult) { const answer = finalResult.result ?? finalResult.message?.content ?? finalResult.message ?? ""; if (answer && typeof answer === "string" && !answer.includes("[object")) { process.stdout.write(answer); } } console.log(); // New line after streaming completes } catch (err: any) { console.error("\nAgent error:", err?.message ?? err); } } rl.close(); } async function main() { try { const agent = await buildAgent(); await chatLoop(agent); } catch (err: any) { console.error("Failed to start agent:", err?.message ?? err); process.exit(1); } } main(); ``` ## Conclusion You've successfully connected Smugmug to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways: - Tool Router dynamically exposes Smugmug tools through an MCP endpoint - LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations - The agent becomes more capable without increasing prompt size - Async Python provides clean, efficient execution of agent workflows You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter. ## 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) - [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 LlamaIndex? Yes, you can. LlamaIndex 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)