How to Use the Currents MCP in Mastra AI

Q: How do I register the Currents MCP Server in Mastra AI?

Instantiate a new MCPClient and pass your Vinkius URL into the servers object. Mastra auto-detects whether you are using SSE or Streamable HTTP.

Q: Can I require human approval for Mastra AI to search Currents?

You set requireToolApproval on the specific search tools. The workflow pauses execution, waits for an administrator to clear the query, and then resumes the news fetch.

Build resilient news monitoring workflows in Mastra AI with automatic retries and conditional branching.

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 Mastra AI

Create your Vinkius account to connect Currents to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fault-Tolerant News Pipelines

Mastra AI executes `get_latest_news` within a structured workflow that expects things to break. If the external news feed times out, the framework's built-in exponential backoff catches the failure and tries again without writing custom loop logic. You validate the connection early in the chain using `check_auth`. This prevents the system from burning cycles on dead requests, letting you branch the workflow to an alert state if the credentials drop.

Conditional Branching by Geography

A global intelligence agent needs to know what territories are trackable before it starts searching. Running `list_regions` and `list_categories` gives your Mastra workflow the exact parameters it needs to decide which execution path to take. If a specific country lacks coverage, the workflow branches to a fallback region automatically. The MCP Server feeds the routing logic the raw data it requires to make those directional choices.

Automated Research with Mastra AI

The `search_news` tool plugs directly into your agent's MCP tool array via `mcpClient.listTools()`. Your workflow takes a broad topic, refines it into a boolean query, and pulls back highly specific articles. Because Mastra handles multi-step operations, you pass these search results into a secondary summarization node. The whole process runs server-side and deploys to any cloud with a single command.

Setup guide

Set up Currents MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Currents tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "currents-mcp-client",
  servers: {
    "currents-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Currents Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Currents tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Currents transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate a new `MCPClient` and pass your Vinkius URL into the servers object. Mastra auto-detects whether you are using SSE or Streamable HTTP.

You set `requireToolApproval` on the specific search tools. The workflow pauses execution, waits for an administrator to clear the query, and then resumes the news fetch.

Pass exact keywords or full boolean strings to the search tool. The agent formulates the string based on the parameters defined in your workflow state.

The framework's built-in retry mechanism catches 429 status codes. It automatically applies exponential backoff, pausing the workflow until the rate limit resets.

The Vinkius runtime destroys the container the second your connection closes. The keyword strings and category filters you pass to the API exist only in memory during the execution phase.

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