# How to integrate Amara MCP with LlamaIndex ```json { "title": "How to integrate Amara MCP with LlamaIndex", "toolkit": "Amara", "toolkit_slug": "amara", "framework": "LlamaIndex", "framework_slug": "llama-index", "url": "https://composio.dev/toolkits/amara/framework/llama-index", "markdown_url": "https://composio.dev/toolkits/amara/framework/llama-index.md", "updated_at": "2026-05-12T10:01:01.046Z" } ``` ## Introduction This guide walks you through connecting Amara to LlamaIndex using the Composio tool router. By the end, you'll have a working Amara agent that can list all subtitle languages for video id, fetch english subtitles for given video, create new spanish subtitle track for video through natural language commands. This guide will help you understand how to give your LlamaIndex agent real control over a Amara account through Composio's Amara MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Amara with - [OpenAI Agents SDK](https://composio.dev/toolkits/amara/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/amara/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/amara/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/amara/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/amara/framework/codex) - [OpenClaw](https://composio.dev/toolkits/amara/framework/openclaw) - [Hermes](https://composio.dev/toolkits/amara/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/amara/framework/cli) - [Google ADK](https://composio.dev/toolkits/amara/framework/google-adk) - [LangChain](https://composio.dev/toolkits/amara/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/amara/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/amara/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/amara/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 Amara - Connect LlamaIndex to the Amara MCP server - Build a Amara-powered agent using LlamaIndex - Interact with Amara 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 Amara MCP server, and what's possible with it? The Amara MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Amara account. It provides structured and secure access to your subtitle and caption management tools, so your agent can perform actions like creating subtitles, managing languages, fetching video metadata, and handling teams on your behalf. - Subtitle creation and editing: Direct your agent to add notes, create new subtitle languages, and fetch subtitle data for any supported video. - Language management: Effortlessly list all available subtitle languages for a given video, retrieve supported language options, or fetch details about specific language tracks. - Video metadata retrieval: Ask your agent to get detailed information about any video URL, including its Amara ID, title, duration, and thumbnails. - Team and user management: Let your agent list all accessible teams, pull details for a specific team, or fetch user data by username or ID for streamlined collaboration. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `AMARA_ADD_SUBTITLE_NOTE` | Add Subtitle Note | Adds a note/comment to a specific subtitle language for a video. Notes are used for collaboration and providing feedback on subtitles during the editing process. Requires a valid video ID and language code. Use this tool to document issues, provide suggestions, or communicate with other subtitle editors. | | `AMARA_ADD_VIDEO_URL` | Add Video URL | Tool to add a new URL to a video, allowing association with multiple video providers (YouTube, Vimeo, etc.). Use when you need to add alternative URLs for the same video content on different platforms. | | `AMARA_CREATE_SUBTITLE_LANGUAGE` | Create Subtitle Language | Creates a new subtitle language track for an Amara video. This is the first step before adding or uploading subtitles - you must create the language track before you can add subtitle content. Each video can have multiple subtitle languages, but you cannot create the same language twice for the same video. Use list_subtitle_languages to check existing languages before creating a new one. | | `AMARA_CREATE_SUBTITLES` | Create Subtitles | Tool to create new subtitles for a video in a specific language. Accepts subtitle data in multiple formats (SRT, VTT, DFXP, etc.) either as a string or via URL. The subtitle language must already exist for the video - use create_subtitle_language first if needed. Use when you need to add subtitle content to a video. | | `AMARA_CREATE_VIDEO` | Create Video | Tool to add a new video to Amara. Use when you need to create a video entry from a URL. Supports URLs from YouTube, Vimeo, Dailymotion, or direct video file URLs. | | `AMARA_DELETE_VIDEO_URL` | Delete Video URL | Tool to remove a video URL from a video. Use when you need to delete an unwanted or incorrect URL from a video's list of URLs. The video must have at least one other URL remaining. | | `AMARA_FETCH_SUBTITLES_DATA` | Fetch Subtitles Data | Fetch subtitle data for a video in a specific language. Returns a list of subtitle segments with start/end timestamps and text content. Use this after obtaining a video ID (from List Videos) and confirming available language codes (from List Subtitle Languages). | | `AMARA_GET_ACTIVITY` | Get Activity | Tool to retrieve detailed information about a specific activity by its ID. Use when you need to fetch metadata for a particular activity event. | | `AMARA_GET_SUBTITLE_LANGUAGE_DETAILS` | Get Subtitle Language Details | Tool to retrieve details for a single subtitle language. Use when you have video ID and language code and need metadata about that language track. | | `AMARA_GET_TEAM_DETAILS` | Get Team Details | Tool to get details on a specific team by slug. Use when you need metadata for a single team. | | `AMARA_GET_TEAM_LANGUAGES` | Get Team Languages | Tool to get language preferences for a specific team by slug. Use when you need to retrieve preferred and blacklisted languages for a team. | | `AMARA_GET_USER_ACTIVITY` | Get User Activity | Tool to retrieve activity log for a specific user on Amara. Use when you need to view a user's recent actions such as video additions, subtitle edits, or comments. Returns a paginated list of activity items with details about what actions the user performed, on which videos, and in which languages. | | `AMARA_GET_USER_DATA` | Get User Data | Retrieves detailed user profile information from Amara, including username, avatar, biography, languages spoken, and video counts. Use this tool when you need to: - Fetch a user's profile details by their username or user ID - Get information about the authenticated user using 'me' as identifier - Look up user metadata like languages, biography, or avatar - Obtain user resource URIs for further API operations Note: User IDs (with 'id$' prefix) are more reliable than usernames since usernames can be changed by users. | | `AMARA_GET_VIDEO_URL` | Get Video URL | Tool to get details for a specific video URL. Use when you need to retrieve metadata about a specific URL entry in Amara's system by video_id and url_id. | | `AMARA_GET_VIDEO_URL_DETAILS` | Get Video URL Details | Tool to get details for a specific video URL. Use when you have a public or embeddable video URL and need its Amara metadata (ID, title, duration, thumbnails, etc.). | | `AMARA_LIST_ACTIVITY` | List Activity | Tool to list activity across Amara. Use when you need to retrieve activity logs with optional filters by team, video, or activity type. | | `AMARA_LIST_AVAILABLE_LANGUAGES` | List Available Languages | Tool to get a list of all supported languages. Use when you need to know available language options from Amara. | | `AMARA_LIST_SUBTITLE_ACTIONS` | List Subtitle Actions | Tool to list available actions for subtitles based on current workflow state. Use when you need to determine what operations can be performed on a subtitle (e.g., approve, reject, publish) for a specific video and language. | | `AMARA_LIST_SUBTITLE_LANGUAGES` | List Subtitle Languages | Tool to list all subtitle languages for a video. Use when you have a video ID and need to fetch its available subtitle languages. | | `AMARA_LIST_SUBTITLE_NOTES` | List Subtitle Notes | List notes for subtitles in a specific language. Use this to retrieve all notes/comments added to a subtitle language for collaboration and feedback purposes. | | `AMARA_LIST_TEAMS` | List Teams | Tool to list all teams. Use when you need to retrieve your accessible teams with pagination. | | `AMARA_LIST_VIDEO_ACTIVITY` | List Video Activity | Tool to list activity for a specific video. Use when you need to fetch the activity log or history of actions performed on a video. | | `AMARA_LIST_VIDEOS` | List Videos | Tool to list all videos. Use when you need to fetch a paginated list of videos with optional filters. | | `AMARA_LIST_VIDEO_URLS` | List Video URLs | Tool to list all URLs associated with a video. Use when you need to retrieve every URL for embedding or processing. | | `AMARA_MAKE_VIDEO_URL_PRIMARY` | Make Video URL Primary | Tool to set a video URL as the primary URL. Use when you need to designate one of a video's URLs as primary for embedding and display. Call after listing video URLs to confirm the URL ID. | | `AMARA_PERFORM_SUBTITLE_ACTION` | Perform Subtitle Action | Tool to perform an action on subtitles such as publish, unpublish, approve, reject, send-back, or endorse. Use when you need to change the workflow state of subtitles for a specific video and language. The available actions depend on the current workflow state and team settings. | | `AMARA_SEND_MESSAGE` | Send Message | Sends a message to a user or team member in Amara. Use this tool to send notifications, updates, or communicate with other users or teams on the platform. You must specify either a recipient user (by username or user ID) or a team (by team slug), but not both. | | `AMARA_UPDATE_SUBTITLE_LANGUAGE` | Update Subtitle Language | Tool to update a subtitle language for a video. Use after reviewing existing subtitle language settings and needing to adjust completeness flags or soft-limit constraints. | | `AMARA_UPDATE_VIDEO` | Update Video | Tool to update an existing video's metadata including title, description, team, and project assignment. Use when you need to modify video information after creation. | | `AMARA_VIEW_VIDEO_DETAILS` | View Video Details | Tool to view details of a specific video by ID. Use when you need complete metadata for a given video. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Amara MCP server is an implementation of the Model Context Protocol that connects your AI agent to Amara. It provides structured and secure access so your agent can perform Amara 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 Amara account and project - Basic familiarity with async Python/Typescript ### 1. Getting API Keys for OpenAI, Composio, and Amara 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 Amara 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, amara) - 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 Amara 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=["amara"], ) 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 Amara actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Amara 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: ["amara"], }, ); 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 Amara 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 Amara ```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 Amara, 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=["amara"], ) 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 Amara actions." system_prompt = """ You are a helpful assistant connected to Composio Tool Router. Use the available tools to answer user queries and perform Amara 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: ["amara"], }, ); 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 Amara 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 Amara to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways: - Tool Router dynamically exposes Amara 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 Amara MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/amara/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/amara/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/amara/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/amara/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/amara/framework/codex) - [OpenClaw](https://composio.dev/toolkits/amara/framework/openclaw) - [Hermes](https://composio.dev/toolkits/amara/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/amara/framework/cli) - [Google ADK](https://composio.dev/toolkits/amara/framework/google-adk) - [LangChain](https://composio.dev/toolkits/amara/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/amara/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/amara/framework/mastra-ai) - [CrewAI](https://composio.dev/toolkits/amara/framework/crew-ai) ## Related Toolkits - [Youtube](https://composio.dev/toolkits/youtube) - YouTube is a leading video-sharing platform for uploading, streaming, and discovering content. It empowers creators and businesses to reach global audiences and monetize their work. - [Cats](https://composio.dev/toolkits/cats) - Cats is an API with a huge library of cat images, breed data, and cat facts. It makes finding adorable cat photos and trivia effortless for your apps and users. - [Chatfai](https://composio.dev/toolkits/chatfai) - Chatfai is an AI platform that lets users talk to AI versions of fictional characters from books, movies, and games. It offers an engaging, interactive experience for fans to chat, roleplay, and explore creative dialogues. - [Cincopa](https://composio.dev/toolkits/cincopa) - Cincopa is a multimedia platform for uploading, managing, and customizing videos, images, and audio. It helps you deliver engaging media experiences with robust APIs and flexible integrations. - [Dungeon fighter online](https://composio.dev/toolkits/dungeon_fighter_online) - Dungeon Fighter Online (DFO) is an arcade-style, side-scrolling action RPG packed with dynamic combat and progression. Play solo or with friends to battle monsters, complete quests, and upgrade your characters. - [Elevenlabs](https://composio.dev/toolkits/elevenlabs) - Elevenlabs is an advanced AI voice generation platform for lifelike, multilingual speech synthesis. Perfect for creating natural voices for videos, apps, and business content in seconds. - [Elevenreader](https://composio.dev/toolkits/elevenreader) - Elevenreader is an AI-powered text-to-speech service by ElevenLabs that converts written content into lifelike audio. It enables fast, natural audio generation from any text. - [Epic games](https://composio.dev/toolkits/epic_games) - Epic Games is a leading video game publisher and digital storefront, known for Fortnite and Unreal Engine. It lets gamers access, manage, and purchase games all in one place. - [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. - [Giphy](https://composio.dev/toolkits/giphy) - Giphy is the largest online library for searching and sharing GIFs and stickers. Instantly add vibrant animated content to your apps, chats, and workflows. - [Headout](https://composio.dev/toolkits/headout) - Headout is a global platform for booking travel experiences, tours, and entertainment. It helps users discover and secure activities at top destinations, all in one place. - [Imagekit io](https://composio.dev/toolkits/imagekit_io) - ImageKit.io is a cloud-based media management platform for image and video delivery. Instantly optimize, transform, and deliver visuals globally via a lightning-fast CDN. - [Listennotes](https://composio.dev/toolkits/listennotes) - Listennotes is a powerful podcast search engine with a massive global database. Discover, search, and curate podcasts from around the world in seconds. - [News api](https://composio.dev/toolkits/news_api) - News api is a REST API for searching and retrieving live news articles from across the web. Instantly access headlines, coverage, and breaking stories from thousands of sources. - [RAWG Video Games Database](https://composio.dev/toolkits/rawg_video_games_database) - RAWG Video Games Database is the largest video game discovery and info service. Instantly access comprehensive details, ratings, and release dates for thousands of games. - [Seat geek](https://composio.dev/toolkits/seat_geek) - SeatGeek is a live event platform offering APIs for concerts, sports, and theater data. Instantly access events, venues, and performers info for smarter ticketing and discovery. - [Shotstack](https://composio.dev/toolkits/shotstack) - Shotstack is a cloud platform for programmatically generating videos, images, and audio. Automate creative content production at scale with flexible RESTful APIs. - [Spotify](https://composio.dev/toolkits/spotify) - Spotify is a streaming service for music and podcasts with millions of tracks from artists worldwide. Enjoy personalized playlists, recommendations, and seamless listening across all your devices. - [Ticketmaster](https://composio.dev/toolkits/ticketmaster) - Ticketmaster is a global platform for event discovery, ticket sales, and live entertainment management. Get real-time access to events and streamline ticketing for fans and organizers. - [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. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Amara MCP? With a standalone Amara MCP server, the agents and LLMs can only access a fixed set of Amara tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Amara 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 Amara tools. ### Can I manage the permissions and scopes for Amara while using Tool Router? Yes, absolutely. You can configure which Amara 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 Amara data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) ยท [Composio docs](https://docs.composio.dev/llms.txt)