How to Use the NewsAPI MCP in Pydantic AI

Q: Is it easy to switch between searching headlines and full articles?

Yes, it's just a different tool call. Your agent would use searchheadlines for headline queries and searcharticles to get full article data. Both return validated Pydantic objects, so the workflow is consistent.

Build reliable agents with Pydantic AI that get structured, validated news data every time you call the NewsAPI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NewsAPI MCP to Pydantic AI

Create your Vinkius account to connect NewsAPI 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 NewsAPI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get validated, type-safe news objects

This is for developers who hate bad data. When your agent calls `search_articles`, the JSON response is automatically parsed and validated against a Pydantic model. You get clean, predictable Python objects every time. If the upstream API ever returns a malformed field or an unexpected `null`, your code raises a `ValidationError` immediately. No more silent failures or defensive coding. You can trust the data your agent is working with.

Build a model-agnostic news agent

Write your tool-using logic once, and run it anywhere. With Pydantic AI, you can build an agent that uses `get_headlines_by_country` and `get_popular_articles`, then swap the underlying LLM from OpenAI to a local Llama model without changing a single line of your tool code. Pydantic AI's `MCPToolset` provides a consistent interface. The framework handles the model-specific prompting, so you can focus on your agent's logic and not the implementation details of the LLM you're using today.

Add 10 NewsAPI tools with one line

There's no need to write custom tool wrappers or API clients. Just instantiate the `MCPToolset` with the Vinkius server URL. Pydantic AI connects to the MCP server and dynamically creates typed methods for all 10 NewsAPI tools. Your agent can immediately call `list_sources()` or `search_headlines()` with full type-hinting and autocompletion in your IDE. It's the fastest way to build a correct, maintainable agent that interacts with news data.

Setup guide

Set up NewsAPI 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": {
        "newsapi-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent NewsAPI 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 NewsAPI. 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 NewsAPI 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 NewsAPI MCP in Pydantic AI

Every response from the NewsAPI MCP server is automatically parsed into a Pydantic model. If any field is missing, has the wrong type, or fails a custom validation rule, Pydantic AI will raise an error immediately.

Yes. Pydantic AI is model-agnostic. You can define your agent's logic using the NewsAPI tools and then connect it to any supported LLM, including local models run via Ollama or llama.cpp.

By default, Pydantic models ignore extra fields, so your code won't break. This makes your agent resilient to non-breaking API changes. You can configure it to raise an error if you require stricter validation.

Yes, it's just a different tool call. Your agent would use `search_headlines` for headline queries and `search_articles` to get full article data. Both return validated Pydantic objects, so the workflow is consistent.

The server processes public news data, including article titles, links, and author names. Vinkius manages authentication with a single, short-lived endpoint token. This means you never have to embed your own NewsAPI key in your agent's code, keeping your credentials secure.

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