# How to integrate DeepSeek MCP with Autogen ```json { "title": "How to integrate DeepSeek MCP with Autogen", "toolkit": "DeepSeek", "toolkit_slug": "deepseek", "framework": "AutoGen", "framework_slug": "autogen", "url": "https://composio.dev/toolkits/deepseek/framework/autogen", "markdown_url": "https://composio.dev/toolkits/deepseek/framework/autogen.md", "updated_at": "2026-10-12T14:18:46.527Z" } ``` ## Introduction This guide walks you through connecting DeepSeek to AutoGen using the Composio tool router. By the end, you'll have a working DeepSeek agent that can summarize latest ai research news, generate chatbot response for user query, search documents for cybersecurity trends through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a DeepSeek account through Composio's DeepSeek MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate DeepSeek with - [Claude Code](https://composio.dev/toolkits/deepseek/framework/claude-code) - [Cursor](https://composio.dev/toolkits/deepseek/framework/cursor) - [ChatGPT](https://composio.dev/toolkits/deepseek/framework/chatgpt) - [Claude Cowork](https://composio.dev/toolkits/deepseek/framework/claude-cowork) - [Antigravity](https://composio.dev/toolkits/deepseek/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/deepseek/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/deepseek/framework/claude-agents-sdk) - [Grok Bot](https://composio.dev/toolkits/deepseek/framework/grok-bot) - [Codex](https://composio.dev/toolkits/deepseek/framework/codex) - [Kimi Code](https://composio.dev/toolkits/deepseek/framework/kimi) - [Grok Build](https://composio.dev/toolkits/deepseek/framework/grok-build) - [VS Code](https://composio.dev/toolkits/deepseek/framework/vscode) - [OpenCode](https://composio.dev/toolkits/deepseek/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/deepseek/framework/openclaw) - [Hermes](https://composio.dev/toolkits/deepseek/framework/hermes-agent) - [Atomic Agent](https://composio.dev/toolkits/deepseek/framework/atomic-agent) - [CLI](https://composio.dev/toolkits/deepseek/framework/cli) - [Google ADK](https://composio.dev/toolkits/deepseek/framework/google-adk) - [LangChain](https://composio.dev/toolkits/deepseek/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/deepseek/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/deepseek/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/deepseek/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/deepseek/framework/crew-ai) - [Pydantic AI](https://composio.dev/toolkits/deepseek/framework/pydantic-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 DeepSeek - Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams - Configure an Autogen AssistantAgent that can call DeepSeek tools - Run a live chat loop where you ask the agent to perform DeepSeek 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 DeepSeek MCP server, and what's possible with it? The DeepSeek MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your DeepSeek account. It provides structured and secure access to DeepSeek models, chat completions, Anthropic-compatible responses, and account balance details, so your agent can generate responses, perform reasoning tasks, use system instructions and tools, check available models, and monitor your balance on your behalf. - Chat response generation: Have your agent use DeepSeek Chat to answer questions, draft content, summarize text, or carry out conversational tasks. - Advanced reasoning: Direct your agent to use DeepSeek Reasoner for tasks that require deeper analysis and structured problem-solving. - Anthropic-compatible conversations: Let the agent create responses with system prompts, tool calling, streaming, or thinking mode through DeepSeek's Anthropic-compatible format. - Model discovery: Instruct your agent to list the DeepSeek models currently available and review their basic ownership and availability details. - Balance monitoring: Have your agent check your current granted and topped-up balances, including the available breakdown in CNY or USD. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `DEEPSEEK_CREATE_ANTHROPIC_MESSAGE` | Create Anthropic Message | Tool to create a model response using DeepSeek's Anthropic-compatible API format with support for system prompts, tool calling, streaming, and thinking mode. Use when you need to generate chat completions using the Anthropic Messages API format. Requires base_url='https://api.deepseek.com/anthropic' or metadata base_url ending with '/anthropic'. Supports extended thinking, function calling with tools, and streaming responses. Note: Images and documents are not supported in content blocks. | | `DEEPSEEK_CREATE_CHAT_COMPLETION` | Create Chat Completion | Tool to create a chat completion using DeepSeek models (deepseek-chat or deepseek-reasoner). Use when you need to generate AI responses to chat conversations. Supports streaming, tool/function calling, and various parameters to control generation behavior (temperature, max_tokens, etc.). | | `DEEPSEEK_GET_USER_BALANCE` | Get User Balance | Tool to get user's current account balance including granted and topped-up balances with detailed breakdown by currency (CNY or USD). Use when you need to check if the user has sufficient balance for API calls or to view detailed balance information. | | `DEEPSEEK_LIST_MODELS` | List Models | Tool to list currently available DeepSeek models and provides basic information about each one such as the owner and availability. Use when you need to discover which models are available for API calls. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The DeepSeek MCP server is an implementation of the Model Context Protocol that connects your AI agents and assistants directly to DeepSeek. Instead of manually wiring DeepSeek 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 DeepSeek 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 DeepSeek 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 DeepSeek 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 DeepSeek 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 DeepSeek session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["deepseek"] ) 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 DeepSeek 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 DeepSeek assistant agent with MCP tools agent = AssistantAgent( name="deepseek_assistant", description="An AI assistant that helps with DeepSeek 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 DeepSeek 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 DeepSeek 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 DeepSeek session composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY")) session = composio.create( user_id=os.getenv("USER_ID"), toolkits=["deepseek"] ) 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 DeepSeek assistant agent with MCP tools agent = AssistantAgent( name="deepseek_assistant", description="An AI assistant that helps with DeepSeek 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 DeepSeek 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 DeepSeek 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 DeepSeek, you can reuse the same structure for other MCP-enabled apps with minimal code changes. ## How to build DeepSeek MCP Agent with another framework - [Claude Code](https://composio.dev/toolkits/deepseek/framework/claude-code) - [Cursor](https://composio.dev/toolkits/deepseek/framework/cursor) - [ChatGPT](https://composio.dev/toolkits/deepseek/framework/chatgpt) - [Claude Cowork](https://composio.dev/toolkits/deepseek/framework/claude-cowork) - [Antigravity](https://composio.dev/toolkits/deepseek/framework/antigravity) - [OpenAI Agents SDK](https://composio.dev/toolkits/deepseek/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/deepseek/framework/claude-agents-sdk) - [Grok Bot](https://composio.dev/toolkits/deepseek/framework/grok-bot) - [Codex](https://composio.dev/toolkits/deepseek/framework/codex) - [Kimi Code](https://composio.dev/toolkits/deepseek/framework/kimi) - [Grok Build](https://composio.dev/toolkits/deepseek/framework/grok-build) - [VS Code](https://composio.dev/toolkits/deepseek/framework/vscode) - [OpenCode](https://composio.dev/toolkits/deepseek/framework/opencode) - [OpenClaw](https://composio.dev/toolkits/deepseek/framework/openclaw) - [Hermes](https://composio.dev/toolkits/deepseek/framework/hermes-agent) - [Atomic Agent](https://composio.dev/toolkits/deepseek/framework/atomic-agent) - [CLI](https://composio.dev/toolkits/deepseek/framework/cli) - [Google ADK](https://composio.dev/toolkits/deepseek/framework/google-adk) - [LangChain](https://composio.dev/toolkits/deepseek/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/deepseek/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/deepseek/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/deepseek/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/deepseek/framework/crew-ai) - [Pydantic AI](https://composio.dev/toolkits/deepseek/framework/pydantic-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. - [AltTextLab](https://composio.dev/toolkits/alt_text_lab) - AltTextLab is an AI service that generates accessible, SEO-aware alt text for images. It helps teams make image content easier to understand, index, and publish. - [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. - [Apiframe](https://composio.dev/toolkits/apiframe) - Apiframe is an API platform for generating and managing AI images, videos, music, uploads, assets, jobs, and custom LoRAs. It gives developers one clean API for creative AI workflows without juggling multiple model providers. - [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. - [Arize AX](https://composio.dev/toolkits/arize_ax) - Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality. - [Artificial Analysis](https://composio.dev/toolkits/artificial_analysis) - Artificial Analysis is an independent benchmarking platform for AI models and API providers. Use it to compare model intelligence, coding, math, pricing, latency, throughput, and arena rankings. - [AssemblyAI](https://composio.dev/toolkits/assemblyai) - AssemblyAI is a speech-to-text and audio intelligence API for uploaded or hosted media. Use it to turn audio and video into accurate transcripts, summaries, and insights. - [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. - [Avoma](https://composio.dev/toolkits/avoma) - Avoma is an AI meeting assistant for recording, transcribing, analyzing, and managing meetings, calls, notes, scorecards, and conversation intelligence. It helps teams turn conversations into searchable notes, follow-ups, coaching insights, and revenue intelligence. - [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. - [Black Forest Labs](https://composio.dev/toolkits/bfl) - Black Forest Labs provides hosted FLUX models for generating and editing images and videos. It offers fast, flexible media creation with asynchronous processing and fine-tuning support. - [Bland AI](https://composio.dev/toolkits/bland_ai) - Bland AI is a conversational AI platform for building voice agents, phone calls, messaging, and communication workflows. Use it to automate calling, evaluate conversations, and run voice operations at scale. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and DeepSeek MCP? With a standalone DeepSeek MCP server, the agents and LLMs can only access a fixed set of DeepSeek tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from DeepSeek 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 DeepSeek tools. ### Can I manage the permissions and scopes for DeepSeek while using Tool Router? Yes, absolutely. You can configure which DeepSeek 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 DeepSeek data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)