How to integrate Hackernews MCP with Autogen

This guide walks you through connecting Hackernews to AutoGen using the Composio tool router. By the end, you'll have a working Hackernews agent that can summarize today's top hacker news stories, find recent posts about ai startups, show comments from this frontpage post through natural language commands. This guide will help you understand how to give your AutoGen agent real control over a Hackernews account through Composio's Hackernews MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Hackernews logoHackernews
No Auth

Hacker News is a tech-focused news aggregator by Y Combinator featuring user-driven stories and discussions on startups and programming. It's a go-to source for trending tech news and thoughtful community insights.

14 Tools

Introduction

This guide walks you through connecting Hackernews to AutoGen using the Composio tool router. By the end, you'll have a working Hackernews agent that can summarize today's top hacker news stories, find recent posts about ai startups, show comments from this frontpage post through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Hackernews account through Composio's Hackernews MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Hackernews with

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 Hackernews
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Hackernews tools
  • Run a live chat loop where you ask the agent to perform Hackernews 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 Hackernews MCP server, and what's possible with it?

The Hackernews MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to the Hacker News platform. It provides structured and secure access to top tech stories, user profiles, and community discussions, so your agent can fetch trending posts, search for news, analyze user activity, and surface the latest updates on your behalf.

  • Frontpage highlights and trending tech stories: Instantly get the current frontpage posts so your agent can summarize or monitor what's hot in tech right now.
  • Smart post search and discovery: Search Hacker News posts by keyword, filter results, and explore relevant discussions tailored to your interests.
  • Real-time updates on new posts: Let your agent fetch the latest or today's posts, keeping you in the loop on breaking news and emerging trends.
  • In-depth post and comment analysis: Retrieve detailed information about any specific Hacker News item, including stories and comment threads, for deeper insights.
  • User profile lookup and insights: Access details about any Hacker News user, helping you analyze activity, contributions, or community reputation.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Hackernews account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard 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.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Hackernews via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

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 Hackernews connections to use
5

Import dependencies and create Tool Router session

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 Hackernews session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["hackernews"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Hackernews tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

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")}
)

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
7

Create the model client and agent

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 Hackernews assistant agent with MCP tools
    agent = AssistantAgent(
        name="hackernews_assistant",
        description="An AI assistant that helps with Hackernews operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Hackernews tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Hackernews 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")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Hackernews 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

Complete Code

Here's the complete code to get you started with Hackernews and AutoGen:

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 Hackernews session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["hackernews"]
    )
    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 Hackernews assistant agent with MCP tools
        agent = AssistantAgent(
            name="hackernews_assistant",
            description="An AI assistant that helps with Hackernews 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 Hackernews 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 Hackernews 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 Hackernews, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Hackernews action and event your agent gets out of the box.

Get Ask HN Story IDs

Get up to 200 latest Ask HN story IDs from Hacker News.

Get Best HackerNews Stories

Get up to 500 best story IDs from HackerNews ranked by score.

Get Hacker News Item

Tool to get a Hacker News item by its unique ID from the Firebase API.

Get Hackernews Item

Get a specific item from Hacker News using its ID.

Get Job Story IDs

Get up to 200 latest job story IDs from Hacker News.

Get Latest Hackernews Posts

Get the latest posts from Hacker News based on optional filters.

Get Max Item ID

Tool to get the current largest item ID from Hacker News.

Get New Hacker News Stories

Get up to 500 newest story IDs from Hacker News.

Get Show HN Stories

Tool to retrieve up to 200 latest Show HN story IDs from Hacker News.

Get Top HackerNews Stories

Get up to 500 top story IDs from HackerNews including jobs.

Get Hacker News Updates

Get recently changed items and user profiles from Hacker News.

Get Hacker News User

Retrieve a Hacker News user's public profile by their username.

Get HackerNews User by Username

Tool to get a user profile by their case-sensitive username from the HackerNews Firebase API.

Search Hackernews Posts

Search Hacker News posts using full-text search powered by Algolia.

FAQ

Frequently asked questions

With a standalone Hackernews MCP server, the agents and LLMs can only access a fixed set of Hackernews tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Hackernews and many other apps based on the task at hand, all through a single MCP endpoint.

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 Hackernews tools.

Yes, absolutely. You can configure which Hackernews 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.

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 Hackernews data and credentials are handled as safely as possible.

Start with Hackernews.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Hackernews tool your agent needs.Free to start.

Start building