# How to integrate Amara MCP with Autogen ```json { "title": "How to integrate Amara MCP with Autogen", "toolkit": "Amara", "toolkit_slug": "amara", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/amara/framework/autogen", "markdown_url": "https://composio.dev/toolkits/amara/framework/autogen.md", "updated_at": "2026-05-12T10:01:01.046Z" } ``` ## Introduction This guide walks you through connecting Amara to AutoGen 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 AutoGen 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) - [LlamaIndex](https://composio.dev/toolkits/amara/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/amara/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 Amara - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call Amara tools - Run a live chat loop where you ask the agent to perform Amara 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 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 agents and assistants directly to Amara. Instead of manually wiring Amara 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 Amara 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 Amara 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 Amara 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 Amara 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 Amara session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["amara"] ) 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 Amara 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 Amara assistant agent with MCP tools agent = AssistantAgent( name="amara_assistant", description="An AI assistant that helps with Amara 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 Amara 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 Amara 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 Amara session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["amara"] ) 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 Amara assistant agent with MCP tools agent = AssistantAgent( name="amara_assistant", description="An AI assistant that helps with Amara 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 Amara 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 Amara 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 Amara, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## 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) - [LlamaIndex](https://composio.dev/toolkits/amara/framework/llama-index) - [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 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 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)