How to Use the NewsCatcher MCP in Pydantic AI

Build type-safe news monitors with Pydantic AI that fail loudly on bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NewsCatcher MCP to Pydantic AI

Create your Vinkius account to connect NewsCatcher 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 NewsCatcher with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce Strict News Schemas

The `search_news` tool returns raw article data that your Pydantic AI agent immediately validates against strict type definitions. You query by keyword and sort by date, and the framework ensures every single field matches your expected model. If the API returns a missing date or a malformed URL, the agent throws a loud validation error. You never get silent corruption or hallucinated variables creeping into your downstream reporting.

Validate Topics via MCP Server

Using the `list_sources` tool, your agent grabs the exact publishers available for a specific topic or language. It validates this array before attempting to read any actual news. The agent then passes these verified publishers into the `get_latest_news` tool. Because the inputs and outputs are strictly typed, your model-agnostic setup works perfectly whether you run it through Claude, OpenAI, or a local model.

Map Complex Story Clusters

The `get_news_clusters` tool delivers grouped narratives that require exact parsing to be useful. Your agent maps these nested clusters into Pydantic models, checking the structure of every single group. You care about correctness. By enforcing types on the clustered output, you guarantee that your application logic only processes valid, well-formed news narratives instead of guessing at the JSON structure.

Setup guide

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

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

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

You instantiate an MCPToolset with your HTTP endpoint URL. You then pass this toolset into your Agent's toolsets parameter.

No, MCPServerHTTP is deprecated. You must use the unified MCPToolset approach to ensure proper tool validation.

The framework throws a runtime validation error immediately. It stops execution rather than letting bad data corrupt your agent's context.

Yes. The framework is completely model-agnostic. As long as the model supports tool calling, it can execute the search operations.

Your specific topic queries and requested source lists are transmitted securely without exposing your application state. The MCP integration guarantees that only the exact parameters required for news retrieval leave your environment, keeping your internal Pydantic models 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