How to Use the Epic Games EOS MCP in Mastra AI

Q: How do I configure the Epic Games EOS MCP Server in Mastra AI?

Initialize a new MCPClient and pass the server URL into the servers object. Mastra auto-detects whether the endpoint uses SSE or Streamable HTTP. Then call listTools() to expose the Epic operations to your agent.

Q: How does Mastra AI handle Epic Games EOS catalog searches?

The agent evaluates your workflow conditions and calls searchstorecatalog when required. It formats the query with your deployment IDs and passes the parsed store items to the next step in your sequence.

Q: Can I require human approval for Epic Games EOS actions in Mastra AI?

You can set requireToolApproval on the client configuration. If the agent tries to pull a friend list, the framework pauses the execution and waits for manual authorization before making the API call.

Build resilient Epic Games backend workflows with automated retries using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Epic Games EOS MCP to Mastra AI

Create your Vinkius account to connect Epic Games EOS 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 Epic Games EOS with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Store Catalog Workflows

The `search_store_catalog` tool on this MCP Server searches the Epic Games Store database using your Sandbox IDs, allowing your Mastra AI agent to programmatically verify item availability. You embed this operation into a conditional workflow that checks for a game and triggers secondary actions based on the result. Network calls to store APIs occasionally fail. Mastra AI wraps this tool in automatic exponential backoff, ensuring your catalog search retries gracefully if the Epic endpoint drops the connection. The workflow engine guarantees the query completes before moving to the next step.

Branch Logic on Account Status

Executing the `get_account_info` tool retrieves public data for specific Epic Account IDs to feed your MCP client's decision tree. If the account exists, the Mastra AI workflow branches to pull the friend list; if it fails, it routes to an error-handling path. You define this logic without writing complex try-catch blocks. The agent evaluates the tool's output and determines the correct path. It keeps your backend code clean while handling the messy realities of player lookups.

Gate Social Data via MCP Server

The `get_friends_list` tool extracts the social graph for a target Epic account. Because this touches user connections, you can configure your Mastra AI client with `requireToolApproval` to pause execution until an admin signs off. The agent stages the request, alerts a human operator, and waits. Once approved, it fires the tool and continues the workflow. This gives you exact control over when and how your system accesses player social data.

Setup guide

Set up Epic Games EOS 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 Epic Games EOS 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: "epic-games-eos-mcp-client",
  servers: {
    "epic-games-eos-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Epic Games EOS 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 Epic Games EOS. 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 Epic Games EOS 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 Epic Games EOS MCP in Mastra AI

Initialize a new `MCPClient` and pass the server URL into the `servers` object. Mastra auto-detects whether the endpoint uses SSE or Streamable HTTP. Then call `listTools()` to expose the Epic operations to your agent.

Yes, the built-in workflow engine handles this natively. If `get_account_info` encounters a timeout, the agent applies an exponential backoff strategy and attempts the fetch again without manual intervention.

The agent evaluates your workflow conditions and calls `search_store_catalog` when required. It formats the query with your deployment IDs and passes the parsed store items to the next step in your sequence.

You can set `requireToolApproval` on the client configuration. If the agent tries to pull a friend list, the framework pauses the execution and waits for manual authorization before making the API call.

The system processes Epic friend lists and associated account IDs strictly within the isolated execution environment. Mastra AI destroys the workflow state immediately after the task completes, leaving zero residual traces of the player's social graph on disk.

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