How to Use the News MCP in Pydantic AI

Build type-safe research pipelines. Connect the News MCP Server to Pydantic AI to validate every breaking headline before your agent acts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect News MCP to Pydantic AI

Create your Vinkius account to connect 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 News with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse Breaking Updates in Pydantic AI

The `get_top_headlines` tool retrieves live news feeds from global outlets. Your agent requests these updates using strict parameter boundaries, never mixing source lists with country or category filters. Pydantic AI forces the raw JSON response into your defined models. If the API drops a critical field or changes a timestamp format, the framework throws a validation error immediately. You catch bad data before it poisons your reasoning loop.

Search 150,000 Outlets via MCP

The `search_everything` tool scans millions of historical articles using AND, OR, NOT, +, and - logic. Your agent executes precise boolean queries to extract specific narratives from a massive media pool. Because Pydantic AI is model-agnostic, you can swap out the underlying LLM at any time. A fast local model can construct the search query, while a heavier Anthropic or OpenAI model processes the resulting text dump.

Index the Publisher Directory

The `list_sources` tool grabs the complete roster of publishers that support top headline tracking. Your agent checks this registry to ensure it only queries valid domains. The unified MCPToolset class handles the HTTP transport natively. The server runs externally on Vinkius, and your agent connects via a single endpoint without managing the underlying connection state.

Setup guide

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

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

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

Instantiate MCPToolset with your Vinkius HTTP endpoint. Pass this object to the toolsets argument in your agent definition. Do not use the deprecated MCPServerHTTP class.

You probably mixed country or category filters with specific source lists. The API strictly forbids this combination. Your agent must choose one filtering strategy per call.

Yes. The search endpoint accepts full boolean logic. You can pass strings containing AND, OR, and NOT operators to isolate exact phrases across millions of articles.

No. The framework validates the tool inputs and outputs regardless of the model. You can use Gemini, Claude, or a local Llama instance to run the search.

The integration processes specific search strings, boolean operators, and requested publisher domains. Vinkius routes these requests through stateless, ephemeral sandboxes. Once the API returns the articles, the sandbox dies, leaving zero trace of your agent's research topics.

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