# How to integrate Ably MCP with CrewAI ```json { "title": "How to integrate Ably MCP with CrewAI", "toolkit": "Ably", "toolkit_slug": "ably", "framework": "CrewAI", "framework_slug": "crew-ai", "url": "https://composio.dev/toolkits/ably/framework/crew-ai", "markdown_url": "https://composio.dev/toolkits/ably/framework/crew-ai.md", "updated_at": "2026-05-12T09:59:50.981Z" } ``` ## Introduction This guide walks you through connecting Ably to CrewAI using the Composio tool router. By the end, you'll have a working Ably agent that can list all active channels and their details, get message history from 'support-chat' channel, show presence history for 'live-event' channel through natural language commands. This guide will help you understand how to give your CrewAI agent real control over a Ably account through Composio's Ably MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Ably with - [OpenAI Agents SDK](https://composio.dev/toolkits/ably/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/ably/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/ably/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/ably/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/ably/framework/codex) - [OpenClaw](https://composio.dev/toolkits/ably/framework/openclaw) - [Hermes](https://composio.dev/toolkits/ably/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/ably/framework/cli) - [Google ADK](https://composio.dev/toolkits/ably/framework/google-adk) - [LangChain](https://composio.dev/toolkits/ably/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/ably/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/ably/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/ably/framework/llama-index) ## TL;DR Here's what you'll learn: - Get a Composio API key and configure your Ably connection - Set up CrewAI with an MCP enabled agent - Create a Tool Router session or standalone MCP server for Ably - Build a conversational loop where your agent can execute Ably operations ## What is CrewAI? CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews. Key features include: - Agent Roles: Define specialized agents with specific goals and backstories - Task Management: Create tasks with clear descriptions and expected outputs - Crew Orchestration: Combine agents and tasks into collaborative workflows - MCP Integration: Connect to external tools through Model Context Protocol ## What is the Ably MCP server, and what's possible with it? The Ably MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ably account. It provides structured and secure access to your real-time messaging infrastructure, so your agent can manage channels, monitor presence, analyze usage, and handle messaging workflows for your applications. - Channel management and creation: Seamlessly create, initialize, or retrieve real-time messaging channels so your agent can orchestrate chat, data sync, and collaboration features on demand. - Presence tracking and analytics: Ask your agent to query current presence states or review historical presence data across multiple channels, gaining insights into user activity and engagement patterns. - Message history and audit: Retrieve detailed message histories from any channel, enabling your agent to audit communication, recover missed messages, or analyze message flows for debugging and compliance. - Push notification subscription management: Let your agent list, manage, or unsubscribe devices from push notification channels, ensuring targeted and controlled delivery of real-time alerts to clients. - Application statistics and monitoring: Have your agent fetch in-depth usage metrics—like message counts, channel activity, and API request stats—so you can monitor health, optimize performance, and manage resources with confidence. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `ABLY_BATCH_PRESENCE` | Query Batch Presence | This tool enables querying the presence states of multiple channels in a single API request. The API retrieves the member presence details of the specified channels in parallel. | | `ABLY_BATCH_PRESENCE_HISTORY` | Query Batch Presence History | This tool enables querying presence history for multiple channels in a single API request. It uses the GET endpoint at https://rest.ably.io/presence to retrieve the member presence history details of the specified channels in parallel. | | `ABLY_DELETE_CHANNEL_SUBSCRIPTION` | Delete Channel Subscription | This tool allows you to unsubscribe devices or clients from push notifications for specific channels. The operation is asynchronous, so immediate requests after deletion may briefly still return the subscription. | | `ABLY_GET_CHANNEL_DETAILS` | Get Channel Details | This tool retrieves metadata and details for a specific channel in Ably. It returns a ChannelDetails object containing information about the channel's status, occupancy, and other metadata. The endpoint provides visibility into channel activity, including metrics such as connections, presence, publishers, and subscribers, and requires appropriate permissions. | | `ABLY_GET_CHANNEL_HISTORY` | Get Channel History | This tool retrieves the message history for a specified Ably channel. It uses the GET /channels/{channelId}/messages endpoint to return a paginated list of messages in chronological order, subject to parameters such as 'channelId', 'limit', 'direction', 'start', and 'end'. The tool is useful for auditing, recovering missed messages, analyzing channel activity, and debugging message flows. Authentication is required via basic or token authentication. | | `ABLY_GET_CHANNEL_PRESENCE` | Get Channel Presence | Tool to obtain the set of members currently present for a channel. Use when you need to check which clients are currently connected and active on a specific Ably channel. | | `ABLY_GET_MESSAGE_VERSIONS` | Get Message Versions | Tool to retrieve all historical versions of a specific message from an Ably channel. Use when you need to track message history, including the original message and all subsequent updates or delete operations. Each version includes metadata such as timestamp, action type, and client ID. | | `ABLY_GET_PRESENCE_HISTORY` | Get Channel Presence History | This tool retrieves the history of presence messages for a specified channel in Ably. It allows you to query presence events on a channel within a given time period. | | `ABLY_GET_PUSH_DEVICE` | Get Push Device Registration | Tool to get the full details of a device registration for push notifications. Use when you need to retrieve information about a specific device registered for push notifications, including its platform, state, recipient details, and metadata. Requires the device ID. | | `ABLY_GET_SERVICE_TIME` | Get Ably Service Time | This tool retrieves the current server time from Ably's service in milliseconds since the epoch. It is particularly useful for time synchronization and generating valid TokenRequest timestamps to prevent replay attacks. The endpoint supports multiple content types, handles HTTP errors, network issues, and is a fundamental tool for ensuring accurate timing in Ably applications. | | `ABLY_GET_STATS` | Get Application Stats | This tool retrieves your application's usage statistics from Ably. The stats endpoint returns a paginated list of your application's usage statistics by minute, hour, day, or month. It supports optional parameters such as start, end, direction, limit, and unit to filter and format the returned data. The stats include metrics for: - Message counts and data transferred - Connection counts - Channel usage - API request counts - Push notification metrics - Token request counts | | `ABLY_LIST_CHANNELS` | List Channels | Tool to enumerate all active channels in the Ably application. Use when you need to discover available channels or monitor channel activity. Returns paginated results and is heavily rate-limited. Can return either channel names only or full channel details with occupancy data. | | `ABLY_LIST_PUSH_CHANNELS` | List Push Channels | Tool to list all channels with at least one subscribed device. Use when you need to discover which channels have active push notification subscriptions in your Ably application. | | `ABLY_LIST_PUSH_CHANNEL_SUBSCRIPTIONS` | List Push Channel Subscriptions | This tool retrieves a list of all push notification channel subscriptions. It allows you to view all active push notification subscriptions for channels in your Ably application. Allows filtering by channel, deviceId, and clientId, supports pagination with limit parameter, and returns detailed push notification subscription information including channel, deviceId, and clientId. | | `ABLY_LIST_REGISTERED_PUSH_DEVICES` | List Registered Push Devices | Tool to list all devices registered for receiving push notifications in your Ably application. Use when you need to view, filter, or audit push notification device registrations. Supports filtering by deviceId and clientId, with pagination via limit parameter. | | `ABLY_PATCH_PUSH_DEVICE_REGISTRATION` | Patch Push Device Registration | Tool to partially update specific attributes of an existing device registration in Ably's push notification system. Use when you need to modify device properties like formFactor, clientId, platform, or push recipient details without replacing the entire registration. | | `ABLY_PUBLISH_BATCH_MESSAGES` | Batch Publish Messages | Tool to batch publish messages to multiple channels in parallel. Use when you need to send the same set of messages to multiple channels simultaneously for efficient broadcasting. | | `ABLY_PUBLISH_MESSAGE_TO_CHANNEL` | Publish Message to Channel | This tool will allow users to publish a message to a specified Ably channel using a POST request. It covers the essentials like channel name, message data, optional event name/type, and additional metadata for push notifications. It is an independent and fundamental operation within Ably's real-time messaging platform. | | `ABLY_PUBLISH_PUSH_NOTIFICATION` | Publish Push Notification | Tool to publish a push notification directly to device(s) via Ably's Push Notifications API. Use when you need to send push notifications to specific devices identified by device ID, client ID, or platform-specific tokens. The API returns HTTP 204 on success with no response body. | | `ABLY_PUBLISH_PUSH_NOTIFICATIONS_BATCH` | Batch Publish Push Notifications | Tool to batch publish push notifications directly to specific recipients. Use when you need to send multiple push notifications efficiently in a single request. Supports up to 10,000 notifications per batch. | | `ABLY_REGISTER_PUSH_DEVICE` | Register Push Device | Tool to register a device for receiving push notifications in Ably. Use when you need to enable push notifications for a specific device across various platforms including iOS (APNs), Android (FCM/GCM), and web browsers (Web Push). The device must be registered before it can receive push notifications through Ably's push notification system. | | `ABLY_REQUEST_ACCESS_TOKEN` | Request Access Token | Request an access token for Ably authentication. Use this when you need to generate a token with specific capabilities and client identifiers for secure authentication. The token can be used to authenticate clients with limited permissions and time-bound access. | | `ABLY_UNREGISTER_ALL_PUSH_DEVICES` | Unregister All Push Devices | Tool to unregister matching devices for push notifications. Use when you need to remove device registrations from Ably's push notification system. You can filter by deviceId or clientId, but not both simultaneously. | | `ABLY_UNREGISTER_PUSH_DEVICE` | Unregister Push Device | Tool to unregister a single device from push notifications in Ably. Use when you need to remove a device's push notification registration. This permanently removes the device from receiving push notifications until it is registered again. | | `ABLY_UPDATE_PUSH_DEVICE` | Update Push Device Registration | Tool to update (upsert) a device registration for push notifications in Ably. Use when registering a new device or updating an existing device's push notification configuration. This is an upsert operation - if the device doesn't exist, it will be created; if it exists, it will be updated. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Ably MCP server is an implementation of the Model Context Protocol that connects your AI agent to Ably. It provides structured and secure access so your agent can perform Ably operations on your behalf through a secure, permission-based interface. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 1. Prerequisites Before starting, make sure you have: - Python 3.9 or higher - A Composio account and API key - A Ably connection authorized in Composio - An OpenAI API key for the CrewAI LLM - Basic familiarity with Python ### 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 **What's happening:** - composio connects your agent to Ably via MCP - crewai provides Agent, Task, Crew, and LLM primitives - crewai-tools[mcp] includes MCP helpers - python-dotenv loads environment variables from .env ```bash pip install composio crewai crewai-tools[mcp] python-dotenv ``` ### 3. Set up environment variables Create a .env file in your project root. What's happening: - COMPOSIO_API_KEY authenticates with Composio - USER_ID scopes the session to your account - OPENAI_API_KEY lets CrewAI use your chosen OpenAI model ```bash COMPOSIO_API_KEY=your_composio_api_key_here USER_ID=your_user_id_here OPENAI_API_KEY=your_openai_api_key_here ``` ### 4. Import dependencies **What's happening:** - CrewAI classes define agents and tasks, and run the workflow - MCPServerHTTP connects the agent to an MCP endpoint - Composio will give you a short lived Ably MCP URL ```python import os from composio import Composio from crewai import Agent, Task, Crew from crewai_tools import MCPServerAdapter import dotenv dotenv.load_dotenv() COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") 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") ``` ### 5. Create a Composio Tool Router session for Ably **What's happening:** - You create a Ably only session through Composio - Composio returns an MCP HTTP URL that exposes Ably tools ```python composio_client = Composio(api_key=COMPOSIO_API_KEY) session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["ably"]) url = session.mcp.url ``` ### 6. Initialize the MCP Server **What's Happening:** - Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication. - MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format. - Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools. - Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops. - Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries. ```python server_params = { "url": url, "transport": "streamable-http", "headers": {"x-api-key": COMPOSIO_API_KEY}, } with MCPServerAdapter(server_params) as tools: agent = Agent( role="Search Assistant", goal="Help users search the internet effectively", backstory="You are a helpful assistant with access to search tools.", tools=tools, verbose=False, max_iter=10, ) ``` ### 7. Create a CLI Chatloop and define the Crew **What's Happening:** - Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable. - Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean. - Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses. - Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context. - Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response. - Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity. ```python print("Chat started! Type 'exit' or 'quit' to end.\n") conversation_context = "" while True: user_input = input("You: ").strip() if user_input.lower() in ["exit", "quit", "bye"]: print("\nGoodbye!") break if not user_input: continue conversation_context += f"\nUser: {user_input}\n" print("\nAgent is thinking...\n") task = Task( description=( f"Conversation history:\n{conversation_context}\n\n" f"Current request: {user_input}" ), expected_output="A helpful response addressing the user's request", agent=agent, ) crew = Crew(agents=[agent], tasks=[task], verbose=False) result = crew.kickoff() response = str(result) conversation_context += f"Agent: {response}\n" print(f"Agent: {response}\n") ``` ## Complete Code ```python from crewai import Agent, Task, Crew, LLM from crewai_tools import MCPServerAdapter from composio import Composio from dotenv import load_dotenv import os load_dotenv() GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not GOOGLE_API_KEY: raise ValueError("GOOGLE_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.") # Initialize Composio and create a session composio = Composio(api_key=COMPOSIO_API_KEY) session = composio.create( user_id=COMPOSIO_USER_ID, toolkits=["ably"], ) url = session.mcp.url # Configure LLM llm = LLM( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY"), ) server_params = { "url": url, "transport": "streamable-http", "headers": {"x-api-key": COMPOSIO_API_KEY}, } with MCPServerAdapter(server_params) as tools: agent = Agent( role="Search Assistant", goal="Help users with internet searches", backstory="You are an expert assistant with access to Composio Search tools.", tools=tools, llm=llm, verbose=False, max_iter=10, ) print("Chat started! Type 'exit' or 'quit' to end.\n") conversation_context = "" while True: user_input = input("You: ").strip() if user_input.lower() in ["exit", "quit", "bye"]: print("\nGoodbye!") break if not user_input: continue conversation_context += f"\nUser: {user_input}\n" print("\nAgent is thinking...\n") task = Task( description=( f"Conversation history:\n{conversation_context}\n\n" f"Current request: {user_input}" ), expected_output="A helpful response addressing the user's request", agent=agent, ) crew = Crew(agents=[agent], tasks=[task], verbose=False) result = crew.kickoff() response = str(result) conversation_context += f"Agent: {response}\n" print(f"Agent: {response}\n") ``` ## Conclusion You now have a CrewAI agent connected to Ably through Composio's Tool Router. The agent can perform Ably operations through natural language commands. Next steps: - Add role-specific instructions to customize agent behavior - Plug in more toolkits for multi-app workflows - Chain tasks for complex multi-step operations ## How to build Ably MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/ably/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/ably/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/ably/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/ably/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/ably/framework/codex) - [OpenClaw](https://composio.dev/toolkits/ably/framework/openclaw) - [Hermes](https://composio.dev/toolkits/ably/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/ably/framework/cli) - [Google ADK](https://composio.dev/toolkits/ably/framework/google-adk) - [LangChain](https://composio.dev/toolkits/ably/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/ably/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/ably/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/ably/framework/llama-index) ## Related Toolkits - [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure. - [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms. - [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place. - [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses. - [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure. - [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure. - [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction. - [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting. - [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache. - [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence. - [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place. - [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines. - [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure. - [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code. - [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows. - [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights. - [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews. - [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease. - [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data. - [Bolt iot](https://composio.dev/toolkits/bolt_iot) - Bolt IoT is a platform for building and managing IoT projects with cloud-based device control and monitoring. It makes connecting sensors and actuators to the internet seamless for automation and data insights. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Ably MCP? With a standalone Ably MCP server, the agents and LLMs can only access a fixed set of Ably tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Ably and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with CrewAI? Yes, you can. CrewAI 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 Ably tools. ### Can I manage the permissions and scopes for Ably while using Tool Router? Yes, absolutely. You can configure which Ably 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 Ably data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)