How to Use the Currents MCP in Google ADK

Q: How do I configure Currents in Google ADK?

Install google-adk and create a McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass this toolset into your LlmAgent initialization. The agent will read the available operations automatically.

Q: Can I limit which news tools the agent sees?

You can use the optional toolnames filter when setting up the toolset. This restricts the agent to specific MCP tools, like only allowing it to run searchnews while hiding the generic feed tools.

Feed real-time news into Gemini agents using Currents and Google ADK.

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 Google ADK

Create your Vinkius account to connect Currents to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fill Gemini's context window with live news

The `get_latest_news` tool injects breaking global articles straight into your prompt. You tell the agent to monitor a topic, and it pulls the raw text from the API. The response feeds directly into your Google Cloud pipeline. Gemini models handle over a million tokens of context. You can dump hundreds of full-length news articles into a single Google ADK session without losing details. The agent reads the entire batch to spot trends across different publications.

Boolean queries for enterprise data sets

Triggering `search_news` allows your agent to run complex boolean queries against millions of historical articles. It filters by exact phrases or excludes specific terms. The MCP Server returns structured JSON matching your exact criteria. Once the agent retrieves this data, it can write the results directly into BigQuery. You combine external news events with your internal enterprise metrics. The framework connects the outside world to your existing Vertex AI infrastructure.

Localize feeds via the Currents MCP Server

Running `list_languages` and `list_regions` tells your agent which localized feeds it can access. It checks the available country codes before requesting foreign press. This prevents the agent from guessing invalid region tags. You can build an intelligence gathering system that tracks specific markets. An agent monitoring European tech startups knows exactly how to query French or German news sources. It adjusts its requests dynamically based on the available options.

Setup guide

Set up Currents MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Currents tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Currents_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Currents tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install `google-adk` and create a `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL. Pass this toolset into your `LlmAgent` initialization. The agent will read the available operations automatically.

You can use the optional `tool_names` filter when setting up the toolset. This restricts the agent to specific MCP tools, like only allowing it to run `search_news` while hiding the generic feed tools.

Enterprise agents need external context to make decisions. This integration feeds real-time global news into your existing Google Cloud architecture. You cross-reference market events with internal data stored in your own databases.

The framework supports both connection methods. Vinkius provides a managed HTTP endpoint, so you will use the network transport for this specific integration. It requires zero local installation.

Your region preferences, category selections, and search strings hit a completely ephemeral container. Vinkius manages the connection through a strict zero-trust model, ensuring your enterprise queries never leak. The sandbox is destroyed the moment the request finishes.

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