How to Use the Newslit MCP in Pydantic AI

Get type-safe media intelligence with Newslit and Pydantic AI for reliable agent behavior.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Newslit MCP to Pydantic AI

Create your Vinkius account to connect Newslit 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 Newslit with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe reporting with Pydantic AI

Every call to `create_report` is validated against your schema at runtime. If the output doesn't match, Pydantic AI stops the execution before errors cascade into your logs. Use `list_reports` to fetch your current inventory. The strict typing ensures your agent always knows exactly what data it is handling.

Retrieve news stories with Pydantic AI

Call `list_stories` to pull verified media data into your agent's memory. Pydantic AI checks every field, ensuring no malformed news snippets enter your pipeline. Use `get_report` to inspect specific details. You get a clear, typed view of your media impact that you can trust.

Manage your PR database in Pydantic AI

Use `update_report` and `delete_report` to maintain your media records. These tools are validated by your models, preventing silent data corruption in your PR database. It gives you a robust way to curate content. Your agent maintains the integrity of your intelligence suite automatically.

Setup guide

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

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

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

It runs the server output through your defined Pydantic models. If the data structure deviates from your requirements, the agent halts immediately.

It is. You connect the server URL directly to the toolset, and your agent treats the Newslit tools as first-class, typed citizens.

Because it eliminates hallucinated fields and silent failures. You get a predictable interface for managing reports that matches your code's expectations.

You can. Since the validation happens at the framework level, you can switch between models while keeping the same Newslit tool integration.

The server operates as a hardened endpoint. It only reads and writes the specific news report objects you authorize, keeping your private media intelligence separate from agent memory.

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