How to Use the Hacker News MCP in Pydantic AI

Q: How do I register the Hacker News MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp and instantiate MCPToolset with your Vinkius HTTP endpoint. Pass this toolset directly into the toolsets list of your Pydantic AI Agent.

Q: Does Pydantic AI validate the Hacker News item schema?

Yes, every Hacker News item retrieved via getitem is validated against strict Pydantic AI models at runtime. If the API format changes, your agent raises a validation error immediately.

Q: Is the HTTP server transport deprecated in the Pydantic AI MCP integration?

Yes, the older MCPServerHTTP class is deprecated. You should use the unified MCPToolset class for all HTTP and SSE connections.

Build type-safe Pydantic AI agents that validate live Hacker News data schemas at runtime before executing model steps.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hacker News MCP to Pydantic AI

Create your Vinkius account to connect Hacker News to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Hacker News with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate front-page stories using this MCP Server

The `top_stories` tool returns the current Hacker News front-page IDs, which are immediately validated against Pydantic AI models at runtime. If the upstream Hacker News API returns corrupted data, your Pydantic AI agent catches the validation error instantly instead of passing bad data to your LLM. You initialize the Hacker News MCP Server connection using `MCPToolset` within your Pydantic AI codebase. This unified approach replaces deprecated Pydantic AI server classes, keeping your Hacker News pipeline clean and maintainable.

Parse structured comments with Pydantic AI

The `get_item` tool fetches individual Hacker News stories, polls, and comments by their unique ID for your Pydantic AI agent. The tool handles the heavy lifting of converting raw Hacker News HTML comments into clean Markdown, which your Pydantic AI agent then validates against your strict runtime schemas. Because the Pydantic AI framework is model-agnostic, you can use these validated Hacker News comments with OpenAI, Anthropic, or local models. You get consistent, type-safe Hacker News data structures regardless of which LLM provider your Pydantic AI agent uses.

Monitor new submissions safely

The `new_stories` tool pulls the latest Hacker News submissions from the active feed directly into your Pydantic AI workflow. Your Pydantic AI agent uses these HN IDs to scan for breaking tech news, validating each payload against your strict python type hints. The Hacker News toolset supports both Streamable HTTP and SSE transports for Pydantic AI. This flexibility allows you to deploy your Pydantic AI agent in any production environment without worrying about transport-level compatibility with the Hacker News server.

Setup guide

Set up Hacker News MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "hacker-news-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Hacker News tools.",
)

result = await agent.run("List recent Hacker News transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Hacker News. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Hacker News now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Hacker News MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and instantiate `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset directly into the `toolsets` list of your Pydantic AI `Agent`.

Yes, every Hacker News item retrieved via `get_item` is validated against strict Pydantic AI models at runtime. If the API format changes, your agent raises a validation error immediately.

Yes, the Pydantic AI framework is model-agnostic. You can run the Hacker News `top_stories` tool with local models or commercial LLM providers while keeping validation strict.

Yes, the older `MCPServerHTTP` class is deprecated. You should use the unified `MCPToolset` class for all HTTP and SSE connections.

The agent only sends item IDs and query parameters to the server. Your system environment variables, API keys, and internal agent states remain entirely local and private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript