How to Use the AccelByte MCP in CrewAI

Q: Can I restrict which AccelByte tools my CrewAI agents can access?

Yes, use the MCPServerHTTP class with a custom toolfilter to limit exposure on your MCP Server. This prevents a support agent from calling administrative tools like deleteclient or banuser.

Run autonomous multi-agent crews to manage AccelByte player support, moderation, and rewards in CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AccelByte MCP to CrewAI

Create your Vinkius account to connect AccelByte 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 AccelByte with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Player Support Crews

The `get_user` tool fetches detailed player profiles to help support agents diagnose account issues. In a multi-agent crew, a triage agent gathers the initial player complaint while a specialist agent retrieves the profile details. If the player reports a missing item, another agent runs `grant_entitlement` to resolve the issue autonomously. This collaborative workflow resolves player tickets without human support staff having to log into separate admin panels.

Autonomous Moderation Teams

The `get_leaderboard` tool scans active rankings to identify suspicious score spikes through the MCP connection. A monitoring agent constantly reviews the leaderboard data and flags suspicious player IDs for review. A separate moderator agent then executes `update_user_status` to temporarily freeze the flagged account while a third agent drafts an audit log. This division of labor prevents false positives by ensuring multiple agents agree before taking action.

Automated Reward Distribution via MCP Server

The `unlock_achievement` tool registers completed milestones on the player's account. Your crew coordinates this process by analyzing gameplay logs and matching them against active challenge lists. Once an achievement is confirmed, a rewards agent calls `get_user_wallets` to verify the player's current balance and logs the event. Let's face it, keeping players rewarded without manual database updates is a massive win.

Setup guide

Set up AccelByte 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 AccelByte tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent AccelByte 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="AccelByte Analyst",
        goal="Access and analyze AccelByte data via MCP.",
        backstory="Expert analyst with direct AccelByte access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent AccelByte 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 AccelByte. 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 AccelByte 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 AccelByte MCP in CrewAI

You pass the Vinkius endpoint URL directly into your agent's `mcps` configuration array. The framework automatically parses the server's tools and makes them available to the crew.

Yes, use the `MCPServerHTTP` class with a custom `tool_filter` to limit exposure on your MCP Server. This prevents a support agent from calling administrative tools like `delete_client` or `ban_user`.

The crew uses a shared memory system to pass authentication states between agents. Once one agent generates a token via `generate_token`, the rest of the crew can access it for subsequent backend calls.

The system supports stdio, SSE, and Streamable HTTP transports. Vinkius manages the hosting, so your Python environment only needs outbound internet access to establish the connection.

Yes, all data remains private because the connection runs through an isolated V8 sandbox. Your credentials and player records are never cached, logged, or exposed to third parties during transit.

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