# How to integrate Honeyhive MCP with Autogen ```json { "title": "How to integrate Honeyhive MCP with Autogen", "toolkit": "Honeyhive", "toolkit_slug": "honeyhive", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/honeyhive/framework/autogen", "markdown_url": "https://composio.dev/toolkits/honeyhive/framework/autogen.md", "updated_at": "2026-05-12T10:15:04.084Z" } ``` ## Introduction This guide walks you through connecting Honeyhive to AutoGen using the Composio tool router. By the end, you'll have a working Honeyhive agent that can add new datapoints to your evaluation dataset, list all datasets in your honeyhive project, log a batch of model events for analysis through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Honeyhive account through Composio's Honeyhive MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Honeyhive with - [OpenAI Agents SDK](https://composio.dev/toolkits/honeyhive/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/honeyhive/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/honeyhive/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/honeyhive/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/honeyhive/framework/codex) - [OpenClaw](https://composio.dev/toolkits/honeyhive/framework/openclaw) - [Hermes](https://composio.dev/toolkits/honeyhive/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/honeyhive/framework/cli) - [Google ADK](https://composio.dev/toolkits/honeyhive/framework/google-adk) - [LangChain](https://composio.dev/toolkits/honeyhive/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/honeyhive/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/honeyhive/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/honeyhive/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/honeyhive/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 Honeyhive - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call Honeyhive tools - Run a live chat loop where you ask the agent to perform Honeyhive 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 Honeyhive MCP server, and what's possible with it? The Honeyhive MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Honeyhive account. It provides structured and secure access to your AI observability platform, so your agent can perform actions like managing datasets, logging model and tool events, evaluating runs, and configuring project settings on your behalf. - Dataset management and organization: Create, retrieve, and delete datasets for your AI projects, helping you maintain organized and up-to-date evaluation data. - Efficient event logging: Log batches of model or external tool events, enabling comprehensive tracking and analysis of AI system interactions in real-time. - Data curation and cleanup: Add new datapoints to datasets or remove specific datapoints, ensuring your evaluation data remains accurate and relevant. - Streamlined evaluation workflows: Mark evaluation runs as completed and fetch project configuration details, making it easy to track progress and update run statuses automatically. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `HONEYHIVE_ADD_DATAPOINTS_TO_DATASET` | Add datapoints to dataset | Tool to add datapoints to a dataset. Use when you need to append multiple entries with specified input, ground truth, and history mappings. | | `HONEYHIVE_COMPARE_RUNS` | Compare Experiment Runs | Tool to retrieve experiment comparison between two evaluation runs. Use when you need to analyze the differences in metrics, datapoints, and events between two runs. | | `HONEYHIVE_COMPARE_RUNS_EVENTS` | Compare Runs Events | Tool to compare events between two experiment runs side-by-side. Use when analyzing differences in model behavior, performance metrics, or outputs between evaluation runs. Returns matched event pairs with their respective data from both runs for comparison. | | `HONEYHIVE_CREATE_BATCH_DATAPOINTS` | Batch Create Datapoints | Tool to create multiple datapoints in a single batch operation. Use when you need to bulk-import events into a dataset or create many datapoints at once. Supports filtering by date range, event IDs, or custom criteria. Efficient for migrating large numbers of events to evaluation datasets. | | `HONEYHIVE_CREATE_BATCH_MODEL_EVENTS` | Create Batch Model Events | Tool to create multiple model events in a single request. Use when you need to log a batch of event interactions to HoneyHive. | | `HONEYHIVE_CREATE_BATCH_TOOL_EVENTS` | Create Batch Tool Events | Tool to log a batch of external API calls as tool events. Use when you need to record multiple tool events in one request—use after gathering all event data. | | `HONEYHIVE_CREATE_CONFIGURATION` | Create Configuration | Creates a new configuration in HoneyHive for managing LLM or pipeline settings. Use this to define reusable configurations with specific models, prompts, and parameters that can be deployed across different environments (dev, staging, prod). Configurations enable version control and environment-specific management of your AI application settings. | | `HONEYHIVE_CREATE_DATAPOINT` | Create Datapoint | Tool to create a new datapoint with input-output pairs. Use when you need to add a single datapoint with inputs, ground truth, conversation history, and metadata. | | `HONEYHIVE_CREATE_DATASET` | Create Dataset | Tool to create a dataset. Use when you need to initialize a new dataset within a project. | | `HONEYHIVE_CREATE_EVENT` | Create Event | Tool to create a new event in HoneyHive to track execution of different parts of your application. Use when you need to log a model call, tool execution, or chain step. Events can be grouped into sessions and nested hierarchically using parent_id and children_ids. | | `HONEYHIVE_CREATE_METRIC` | Create Metric | Tool to create a new metric in HoneyHive. Use when you need to define how to evaluate model outputs, whether through code (PYTHON), AI evaluation (LLM), human review (HUMAN), or combining multiple metrics (COMPOSITE). Important: LLM metrics require both model_provider and model_name to be specified. | | `HONEYHIVE_CREATE_MODEL_EVENT` | Create Model Event | Tool to create a new model event to log LLM call data. Use when you need to track a single model interaction including messages, responses, usage, and metadata. | | `HONEYHIVE_CREATE_TOOL` | Create Tool | Creates a new tool definition in a HoneyHive project. Use this to register functions or plugins that can be invoked and tracked within HoneyHive. Tools are defined with a JSON Schema for their parameters, allowing HoneyHive to validate inputs and track tool usage in your AI workflows. Tool names must be unique within a project. | | `HONEYHIVE_DELETE_DATAPOINT` | Delete Datapoint | Tool to delete a specific datapoint by its ID. Use when you need to remove a datapoint from HoneyHive after confirming its identifier. | | `HONEYHIVE_DELETE_DATASET` | Delete Dataset | Tool to delete a dataset by ID. Use when you need to remove a dataset after confirming its ID. | | `HONEYHIVE_END_EVALUATION_RUN` | End Evaluation Run | Tool to update an evaluation run's status and metadata. Use to mark a run as completed after finishing evaluations, or update run properties like name, metadata, configuration, and associated event/datapoint IDs. | | `HONEYHIVE_GET_CONFIGURATIONS` | Get Configurations | Tool to retrieve a list of configurations. Use when you need to fetch all configurations for a specific project before making changes. | | `HONEYHIVE_GET_DATASETS` | Get Datasets | Retrieve datasets from HoneyHive for a specified project. Use this tool when you need to: - List all datasets within a project - Find datasets by type (evaluation or fine-tuning) - Retrieve a specific dataset by its ID Returns dataset details including name, description, datapoints count, type, and timestamps. | | `HONEYHIVE_GET_EVENTS` | Get Events | Tool to query events with filters and projections from HoneyHive. Use this action when you need to retrieve events with lightweight filtering (limit 1000 results). For bulk exports or more complex queries, use the Retrieve Events action instead. Supports filtering by date range, event properties, and field projections. | | `HONEYHIVE_GET_EVENTS_BY_SESSION_ID` | Get Events By Session ID | Tool to retrieve the complete tree of nested events for a specific session. Use when you need to analyze all events (model calls, tool calls, chains) that occurred within a session, including their hierarchical relationships, inputs, outputs, metrics, and costs. Returns a tree structure with recursive children. | | `HONEYHIVE_GET_EVENTS_CHART` | Get Events Chart | Tool to retrieve charting and analytics data for events over time. Use when you need aggregated metrics (duration, cost, token usage) grouped by time buckets or fields. Supports percentile analysis (p50, p95, p99) for latency monitoring and custom filters for targeted analytics. | | `HONEYHIVE_GET_METRICS` | Get Metrics | Retrieves all metrics associated with a HoneyHive project. Returns a list of metrics including their configuration (name, type, description, thresholds, evaluator details) and metadata (creation/update timestamps, sampling settings). Use this tool when you need to: - List all metrics configured for a project - Get metric IDs for updating metrics via HONEYHIVE_UPDATE_METRIC - Understand what evaluations are set up for a project Prerequisites: Obtain a valid project_name using HONEYHIVE_GET_PROJECTS first. | | `HONEYHIVE_GET_PROJECTS` | Get Projects | Tool to retrieve all projects in the HoneyHive account. Use when you need to list available projects, get project IDs for use in other API calls, or search for a specific project by name. | | `HONEYHIVE_GET_RUN` | Get Evaluation Run Details | Tool to get details of an evaluation run by its UUID. Use when you need to check the status, configuration, results, or metadata of a specific evaluation run. | | `HONEYHIVE_GET_RUN_METRICS` | Get Run Metrics | Tool to get event metrics for an experiment run. Use when you need to retrieve metrics computed on events within a specific experiment run. Returns an array of event objects with their associated metrics, which can be filtered by date range or custom filters. | | `HONEYHIVE_GET_RUNS` | Get Evaluation Runs | Tool to retrieve a list of evaluation runs from HoneyHive. Use when you need to: - List all evaluation runs for analysis - Find runs by status, name, or dataset - Get specific runs by their IDs - Paginate through large sets of evaluation runs Returns evaluation details including status, results, configuration, and timestamps. | | `HONEYHIVE_GET_RUNS_SCHEMA` | Get Runs Schema | Tool to retrieve the schema for experiment runs in HoneyHive. Use when you need to understand available fields, datasets, and mappings for experiment runs. | | `HONEYHIVE_GET_SESSION` | Get Session | Retrieve a complete session tree by session ID from HoneyHive. Use this tool to fetch the full session hierarchy including all nested events (model calls, tool calls, chains) with their inputs, outputs, durations, and metadata. Returns a recursive tree structure with aggregated metrics. Prerequisites: You need a valid session ID from HONEYHIVE_START_SESSION or HONEYHIVE_RETRIEVE_EVENTS. | | `HONEYHIVE_LIST_TOOLS` | List Tools | Tool to list all available Honeyhive tools. Use when you need to discover which functions or plugins are registered for use. | | `HONEYHIVE_RETRIEVE_DATAPOINT` | Retrieve Datapoint | Retrieve a specific datapoint by its ID from HoneyHive. Use this tool when you need the full details of a single datapoint, including its inputs, ground truth, conversation history, linked datasets, and metadata. Prerequisites: You need a valid datapoint ID. Get datapoint IDs from: - HONEYHIVE_RETRIEVE_DATAPOINTS (list datapoints by project/dataset) - HONEYHIVE_ADD_DATAPOINTS_TO_DATASET (returns IDs of newly created datapoints) | | `HONEYHIVE_RETRIEVE_DATAPOINTS` | Retrieve Datapoints | Retrieve datapoints from a HoneyHive project. Use this tool to fetch evaluation datapoints containing inputs, ground truth, and metadata. Supports filtering by specific datapoint IDs or dataset name. Commonly used to: - Review existing test cases before running evaluations - Export datapoints for analysis - Verify datapoint contents after adding them to a dataset | | `HONEYHIVE_RETRIEVE_EVENTS` | Retrieve Events | Retrieve and export events from a HoneyHive project. Use this tool to query traced events (model calls, tool calls, sessions, chains) with optional filters by event_type, metadata, feedback scores, or date range. Returns events with their inputs, outputs, duration, and metrics. Supports pagination for large result sets (max 7500 per page). | | `HONEYHIVE_RETRIEVE_EXPERIMENT_RESULT` | Retrieve Experiment Result | Tool to retrieve the result of a specific experiment run. Use when you need the status, metrics, and datapoint-level details of a completed experiment. | | `HONEYHIVE_START_EVALUATION_RUN` | Start Evaluation Run | Creates a new evaluation run to group and track multiple session events for analysis. Use this action when you want to: - Compare model performance across multiple sessions - Create evaluation batches for quality assurance - Link existing events to datasets for structured evaluation Prerequisites: - Get project ID using Get Projects action - Get event IDs from Start Session or Retrieve Events actions - (Optional) Get dataset ID from Get Datasets action | | `HONEYHIVE_START_SESSION` | Start Session | Start a new HoneyHive session for tracing and observability. Use this tool to initiate a tracking session that groups together related model, tool, and chain events. Returns a session_id that should be used to link subsequent events to this session. Common use cases: - Start tracing a user conversation - Begin logging an LLM pipeline execution - Initialize observability for a batch processing job | | `HONEYHIVE_UPDATE_CONFIGURATION` | Update Configuration | Tool to update an existing HoneyHive configuration. Use when you need to modify a configuration's name, provider, model parameters, environments, or other settings. You must provide the configuration ID (obtainable via Get Configurations action) and the name field. All other fields are optional and will only update if provided. | | `HONEYHIVE_UPDATE_DATAPOINT` | Update Datapoint | Update an existing datapoint by ID. Use this to modify any combination of inputs, ground_truth, history, metadata, linked_datasets, or linked_evals for a datapoint. Requires a valid datapoint ID obtained from retrieve_datapoints or add_datapoints_to_dataset. | | `HONEYHIVE_UPDATE_DATASET` | Update Dataset | Tool to update an existing dataset. Use when you need to modify a dataset's details (name, description, datapoints, linked evaluations, or metadata) after confirming its ID. | | `HONEYHIVE_UPDATE_EVENT` | Update Event | Update an existing HoneyHive event by ID. Use to attach feedback, metrics, metadata, outputs, config, user properties, or update duration on events created via start_session or batch event creation. At least one optional field must be provided alongside the event_id. | | `HONEYHIVE_UPDATE_METRIC` | Update Metric | Tool to update an existing metric. Use when you need to modify a metric’s properties after creation. Ensure you retrieve the metric first to verify its current state. | | `HONEYHIVE_UPDATE_PROJECT` | Update Project | Updates an existing HoneyHive project's name or description. Use this action to modify project metadata after creation. You must provide the project_id and at least one field to update (name or description). To find project IDs, use the Get Projects action first. | | `HONEYHIVE_UPDATE_TOOL` | Update Tool | Tool to update an existing tool in HoneyHive. Use when you need to modify a tool's name, description, parameters, or type after confirming its ID. At least one optional field must be provided alongside the required tool ID. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Honeyhive MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to Honeyhive. Instead of manually wiring Honeyhive 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 Honeyhive 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 Honeyhive 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 Honeyhive 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 Honeyhive 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 Honeyhive session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["honeyhive"] ) 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 Honeyhive 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 Honeyhive assistant agent with MCP tools agent = AssistantAgent( name="honeyhive_assistant", description="An AI assistant that helps with Honeyhive 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 Honeyhive 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 Honeyhive 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 Honeyhive session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["honeyhive"] ) 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 Honeyhive assistant agent with MCP tools agent = AssistantAgent( name="honeyhive_assistant", description="An AI assistant that helps with Honeyhive 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 Honeyhive 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 Honeyhive 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 Honeyhive, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## How to build Honeyhive MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/honeyhive/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/honeyhive/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/honeyhive/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/honeyhive/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/honeyhive/framework/codex) - [OpenClaw](https://composio.dev/toolkits/honeyhive/framework/openclaw) - [Hermes](https://composio.dev/toolkits/honeyhive/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/honeyhive/framework/cli) - [Google ADK](https://composio.dev/toolkits/honeyhive/framework/google-adk) - [LangChain](https://composio.dev/toolkits/honeyhive/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/honeyhive/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/honeyhive/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/honeyhive/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/honeyhive/framework/crew-ai) ## Related Toolkits - [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed. - [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service. - [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows. - [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow. - [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows. - [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application. - [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities. - [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization. - [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications. - [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations. - [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key. - [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient. - [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions. - [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences. - [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement. - [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team. - [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs. - [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code. - [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets. - [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Honeyhive MCP? With a standalone Honeyhive MCP server, the agents and LLMs can only access a fixed set of Honeyhive tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Honeyhive 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 Honeyhive tools. ### Can I manage the permissions and scopes for Honeyhive while using Tool Router? Yes, absolutely. You can configure which Honeyhive 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 Honeyhive data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)