How to Use the Froged MCP in Mastra AI

Q: Can I require human approval before my agent sends a message in Froged with Mastra AI?

Yes. Mastra AI supports requireToolApproval. You can configure your workflow so that any call to sendchatmessage pauses and waits for a human to approve it. This is great for semi-automated support.

Q: How can I build a workflow that reacts to specific user actions in Froged with Mastra AI?

Have your agent poll the listbehavioralevents tool. Your workflow can then trigger different actions based on the event names it finds, like sending a follow-up email when a user's trial is about to expire.

Q: Does this MCP server let me see the full chat history?

It does. The getchatdetails tool returns the entire conversation history for a given chat ID. Your Mastra AI agent can use this data to understand the full context before taking action.

Build failure-proof Froged workflows with Mastra AI. Automate customer onboarding and support with built-in retries and logic.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Froged MCP to Mastra AI

Create your Vinkius account to connect Froged 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 Froged with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate new user onboarding

Use this MCP server to build a rock-solid onboarding workflow. When a user signs up, your Mastra AI agent can call `upsert_contact` to create their record in Froged. Then, it can log a 'signup' event with `track_custom_event`. Here's the thing: Mastra AI's engine handles the logic. If the `upsert_contact` call fails because of a network issue, the engine will automatically retry. You don't write that code; you just define the steps, and it makes sure they happen.

Build conditional support escalation logic

Create smart support routing without writing a ton of `if/else` statements. Your agent can grab new tickets from `list_support_conversations`, then use `get_contact_details` to check if the user has a 'VIP' tag. Mastra AI lets you branch the workflow based on that data. If the user is a VIP, the agent can escalate the issue. If not, it can try to find an answer using `list_kb_articles` and reply with `send_chat_message`. It's a simple way to build complex, stateful automation.

Reliably sync marketing and user data

Your Mastra AI agent can act as a data steward between systems. Set up a workflow that periodically calls `list_marketing_campaigns` and `list_cs_contacts` to keep an external data warehouse in sync with Froged. The built-in scheduler and retry logic mean you can trust it to run. Before executing, the workflow can ping `verify_api_status` to ensure Froged is available, preventing failed runs and unnecessary alerts. This is how you build dependable background jobs.

Setup guide

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

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

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

In your agent's configuration, just add your Vinkius URL to the `servers` property of the `MCPClient`. Mastra AI automatically detects the transport and makes all the Froged tools available to your workflows.

Yes. Mastra AI supports `requireToolApproval`. You can configure your workflow so that any call to `send_chat_message` pauses and waits for a human to approve it. This is great for semi-automated support.

Have your agent poll the `list_behavioral_events` tool. Your workflow can then trigger different actions based on the event names it finds, like sending a follow-up email when a user's trial is about to expire.

It does. The `get_chat_details` tool returns the entire conversation history for a given chat ID. Your Mastra AI agent can use this data to understand the full context before taking action.

Your agents will handle Froged contact records, chat conversations, and custom event data. The Vinkius platform ensures your Froged API key is never part of your agent's code. All connections go through a single, authenticated endpoint and are executed in a zero-trust environment.

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