How to Use the Currents MCP in OpenAI Agents SDK

Q: How do I add Currents to the OpenAI Agents SDK?

Install the openai-agents package via pip. Create an MCPServerStreamableHttp instance with your Vinkius URL and pass it to the Agent constructor in the mcpservers list. The tools auto-discover immediately.

Q: Can the agent cache the available news tools?

Yes, you can set cacheToolsList=True during setup. This prevents the framework from fetching the tool definitions on every single run. It speeds up your execution time significantly.

Build production-ready news agents with Currents and the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Currents to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Production news feeds with OpenAI Agents SDK

The `get_latest_news` tool pulls real-time global headlines directly into your agent's context. Instead of scraping random sites, your production system queries a structured API for breaking updates. You get clean text ready for summarization or sentiment analysis. Because you are using the OpenAI framework, you can wrap this fetch in strict guardrails. If a sub-agent pulls news outside its permitted scope, the system blocks the execution before it happens. Tracing in the OpenAI dashboard shows exactly when the agent decided to check the news.

Search archives across specialized agents

Executing `search_news` lets your agent query millions of articles using boolean logic or specific keywords. You supply the parameters, and the MCP Server returns targeted historical data. The agent filters out noise before passing the context downstream. This fits perfectly into a multi-agent setup. A research agent runs the search, grabs the relevant articles, and hands off the payload to a financial analyst agent. You build complex workflows where one specialist fetches the data and another acts on it.

Filter feeds by language and region

Calling `list_categories`, `list_languages`, and `list_regions` exposes exactly what content filters are available. Your agent reads these lists to understand its constraints before attempting a search. It knows exactly which country codes and language tags it can use. You never have to hardcode these parameters in your Python script. The agent dynamically discovers the supported regions at runtime via the MCP protocol. It adapts on the fly if the underlying API adds new languages.

Setup guide

Set up Currents MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Currents tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Currents tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Currents tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Currents Agent",
            instructions="You have access to Currents tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the `openai-agents` package via pip. Create an `MCPServerStreamableHttp` instance with your Vinkius URL and pass it to the Agent constructor in the `mcp_servers` list. The tools auto-discover immediately.

Yes, you can set `cacheToolsList=True` during setup. This prevents the framework from fetching the tool definitions on every single run. It speeds up your execution time significantly.

Writing your own integration means maintaining API contracts and handling errors manually. This MCP Server gives your agent immediate access to `search_news` while keeping the strict guardrails and tracing native to the framework. You focus on logic, not plumbing.

No, Vinkius handles the underlying authentication. Your script only needs the single endpoint token to connect. The `check_auth` tool verifies your connection status before running heavy queries.

The server processes search keywords, boolean queries, and requested language codes. It runs inside a V8 Isolate Sandbox on Vinkius, meaning your parameters execute in a zero-trust, ephemeral environment. No search history persists after the session closes.

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