How to Use the Currents MCP in Pydantic AI

Q: How do I connect Currents to Pydantic AI?

Install pydantic-ai-slimmcp via pip. Create an MCPToolset pointing to your Vinkius HTTP endpoint and pass it to your Agent's toolsets parameter. Remember that MCPServerHTTP is deprecated in favor of the unified toolset approach.

Q: Can I verify my connection before running queries?

You can call the checkauth tool to confirm your API status. This is useful for running a quick health check during your application startup sequence. It ensures the endpoint is reachable.

Type-safe news retrieval for your agents using Currents and Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Currents MCP to Pydantic AI

Create your Vinkius account to connect Currents 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 Currents with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe news feeds with Pydantic AI

The `get_latest_news` tool fetches breaking articles while your framework guarantees the data structure. You define exactly what fields the agent expects to receive. The API returns real-time updates from global sources. If the news provider changes their payload, your agent fails loudly with a runtime validation error. There is no silent corruption or hallucinated text creeping into your application. You know exactly what data you are working with before the agent processes it.

Search archives across any LLM

Using `search_news` gives your agent the ability to run keyword and boolean queries against a massive article database. The agent constructs the search parameters based on user prompts. It pulls historical data to answer specific research questions. Because this framework is model-agnostic, you can swap out the underlying LLM at any time. You might use a local model for drafting the search queries and Anthropic for summarizing the results. The MCP Server works identically regardless of which brain powers the agent.

Discover categories via the Currents MCP Server

The `list_categories` and `list_regions` tools provide the exact constraints your agent needs to build valid requests. It reads the supported news topics directly from the source. The agent never guesses which categories exist. This dynamic discovery pairs perfectly with strict typing. The agent pulls the valid regions, validates them against your internal models, and then executes a perfectly formatted search. You eliminate bad requests before they ever hit the network.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` via pip. Create an `MCPToolset` pointing to your Vinkius HTTP endpoint and pass it to your Agent's `toolsets` parameter. Remember that `MCPServerHTTP` is deprecated in favor of the unified toolset approach.

Yes, the framework is completely model-agnostic. As long as your local LLM supports function calling, it can read the tool definitions and execute searches.

Writing custom fetch logic means manually parsing JSON and hoping the structure stays consistent. This integration offloads the API work to the MCP standard while your framework enforces strict runtime validation. You guarantee correctness at every step.

You can call the `check_auth` tool to confirm your API status. This is useful for running a quick health check during your application startup sequence. It ensures the endpoint is reachable.

The specific boolean operators and keywords your agent generates are processed inside an isolated V8 sandbox. Vinkius routes the request through a secure gateway where no data is logged or retained. Your research topics remain entirely confidential.

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