How to Use the Epic Games EOS MCP in CrewAI

Q: How do I connect the Epic Games EOS MCP Server to a CrewAI agent?

Pass the server URL directly into the mcps array on your Agent definition. For granular control, import MCPServerHTTP, configure it with the endpoint, and use a tool filter to expose specific Epic operations.

Q: Can multiple agents share Epic account data?

Yes. One agent can call getaccountinfo and store the resulting profiles in the shared crew memory. Subsequent agents in the hierarchy can read this data to perform their own specialized tasks.

Q: How do I restrict a CrewAI agent to only search the Epic Games EOS catalog?

Use the toolfilter parameter when initializing the server connection. This ensures your specific agent only sees searchstorecatalog and ignores the account or friend list tools.

Deploy autonomous multi-agent teams to monitor and analyze Epic Games player data using CrewAI.

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 CrewAI

Create your Vinkius account to connect Epic Games EOS to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign Account Lookups to Specialists

The `get_account_info` tool on this MCP Server fetches public profile data for Epic Account IDs, allowing you to assign player verification entirely to a dedicated researcher agent. This agent takes a list of raw IDs, runs the tool, and passes the formatted profiles to a secondary analyst agent. Instead of writing a monolithic script, you divide the labor. The researcher focuses strictly on pulling the correct account details. It uses shared memory to store the results, ensuring the rest of the crew has accurate player identities before taking action.

Map Social Graphs Autonomously

Running the `get_friends_list` tool pulls the complete social network for a specific Epic account into your CrewAI MCP session. A dedicated mapping agent iterates through these connections, calling the tool repeatedly to build a deep social tree. The crew handles this without human intervention. A moderator agent watches the execution to ensure the mapping agent respects rate limits. If the process hits a snag, the team adjusts its strategy and continues building the network map.

Delegate Catalog Searches via MCP Server

The `search_store_catalog` tool queries the Epic Games Store database using your Sandbox IDs so a specialized commercial agent can track item availability. You give the agent a list of target games, and it autonomously executes the searches across the catalog. You load this capability by passing the HTTP endpoint to the `MCPServerHTTP` class with a `tool_filter`. This restricts your commercial agent so it can only search the store, preventing it from accidentally pulling unrelated account data.

Setup guide

Set up Epic Games EOS MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Epic Games EOS tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Epic Games EOS Analyst",
    goal="Access and analyze Epic Games EOS data via MCP.",
    backstory="Expert analyst with direct Epic Games EOS access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Epic Games EOS transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Epic Games EOS Analyst",
        goal="Access and analyze Epic Games EOS data via MCP.",
        backstory="Expert analyst with direct Epic Games EOS access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Epic Games EOS transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the server URL directly into the `mcps` array on your Agent definition. For granular control, import `MCPServerHTTP`, configure it with the endpoint, and use a tool filter to expose specific Epic operations.

Yes. One agent can call `get_account_info` and store the resulting profiles in the shared crew memory. Subsequent agents in the hierarchy can read this data to perform their own specialized tasks.

Use the `tool_filter` parameter when initializing the server connection. This ensures your specific agent only sees `search_store_catalog` and ignores the account or friend list tools.

You can configure your crew to run sequentially. Agent A pulls the account ID, Agent B uses that ID to fetch the friend list, and Agent C cross-references those friends against store catalog purchases.

The agents process Epic Account IDs and public display names entirely within the V8 Isolate Sandbox memory space. CrewAI flushes the shared context window the moment the final agent completes its task, ensuring no persistent storage of player identifiers.

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