How to Use the Mercury MCP in Mastra AI

Q: Can Mastra AI retry a failed Mercury recipient creation?

Yes. If createrecipient times out, Mastra's workflow engine uses its native retry logic to attempt the operation again without crashing your application.

Q: How does human-in-the-loop work with Mercury and Mastra AI?

You configure approval rules on high-risk MCP tools like createrecipient. This pauses the execution thread until an administrator verifies the routing details.

Q: Can I list team members within a workflow?

Yes, calling listteammembers allows your workflow to verify if an active user has permission to request specific financial reports before proceeding.

Build resilient Mastra AI workflows that automate Mercury treasury checks and handle banking failures with built-in retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercury MCP to Mastra AI

Create your Vinkius account to connect Mercury 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 Mercury with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate treasury checks with Mastra AI workflows

`get_treasury_balance` triggers your automated financial workflows whenever liquidity drops below a specific threshold. Mastra AI evaluates this numeric output and decides whether to alert your executive team. By running `list_accounts` in your initial workflow step, the agent maps your entire cash distribution across multiple entities. You don't have to hardcode account IDs because the framework handles the lookup dynamically.

Build resilient Mercury MCP Server workflows

Run `create_recipient` within a Mastra workflow that automatically retries the operation if the bank's API rate limit is reached. Here's the deal: the built-in exponential backoff ensures your setup doesn't fail due to temporary network hiccups. If the recipient registry fails validation, the workflow branches to notify your team via email. This keeps your ledger accurate without letting silent errors slip through.

Enforce human approvals for Mercury statement exports

Fetching statements via `list_statements` can be gated using Mastra's tool approval setting. This stops your agent from exporting sensitive PDFs until a manager explicitly clicks approve in your control panel. Once approved, the system executes `list_transactions` to verify the statement dates match your internal database. You get automated compliance checks without giving up human control.

Setup guide

Set up Mercury 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 Mercury 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: "mercury-mcp-client",
  servers: {
    "mercury-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Mercury 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 Mercury. 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 Mercury 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 Mercury MCP in Mastra AI

Initialize the MCP client with your Vinkius endpoint, then pass `get_treasury_balance` directly to your agent's tool array. The framework handles the transport protocol automatically.

Yes. If `create_recipient` times out, Mastra's workflow engine uses its native retry logic to attempt the operation again without crashing your application.

You configure approval rules on high-risk MCP tools like `create_recipient`. This pauses the execution thread until an administrator verifies the routing details.

Yes, calling `list_team_members` allows your workflow to verify if an active user has permission to request specific financial reports before proceeding.

Your bank statements and payment records are protected by ephemeral, zero-trust MCP sandboxes. The workflow engine processes these payloads in memory without caching your financial secrets.

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