How to Use the Decentraland (Virtual World Content API) MCP in OpenAI Agents SDK

Q: How do I initialize Decentraland (Virtual World Content API) inside the OpenAI Agents SDK?

Install the package, define your server parameters using MCPServerStreamableHttp, and pass it to your Agent constructor. The MCP Server exposes fifteen available tools that the SDK automatically discovers at runtime.

Q: Can the OpenAI Agents SDK filter wearables using this Decentraland (Virtual World Content API) server?

Yes. Your agent calls getmarketplacecatalog with specified filters to parse the active item list. The SDK handles the argument passing directly, returning structured JSON to the model.

Q: How does the agent track active server instances?

Your agent runs getrealms to fetch active server instances and their current user loads. It then queries getmainrealmabout to determine the best connection target.

Track hot parcels and trigger Decentraland events directly from your OpenAI Agents SDK setup using this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Decentraland (Virtual World Content API) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Decentraland (Virtual World Content API) to OpenAI Agents SDK 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 Decentraland (Virtual World Content API) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track Live Land Metrics inside OpenAI Agents SDK

The `get_parcel_stats` tool exposes real-time user distribution across Genesis City coordinates directly to your agent. Python developers write zero parsing logic because the SDK automatically registers this tool and feeds raw coordinate metrics into the agent's context. Your agent inspects land traffic patterns by combining this coordinate data with `get_hot_scenes` to pinpoint active hubs instantly. This setup lets autonomous scripts monitor virtual real estate trends without polling raw HTTP endpoints manually.

Managed Event Operations via MCP Server

The `create_event` tool requires user authentication to publish new virtual gatherings directly from your Python runtime. By hooking this MCP Server into your agent setup, you allow the model to draft, schedule, and publish events based on market demand. Users authenticate securely using `create_auth_request` and verify their status via `get_auth_request`. Once verified, your agent pulls their schedules using `list_attending_events` to manage land calendars without leaving the OpenAI orchestration loop.

Automated Marketplace Queries

The `get_marketplace_catalog` tool lists active wearables and emotes using native SDK schemas. Your agent queries this catalog to track price floors and item metadata without hardcoded API clients. If a user asks for trading history, the agent invokes `get_marketplace_items` to pull historical sales. Every call is traced automatically by the OpenAI framework, giving you a clear debug log of every blockchain query.

Setup guide

Set up Decentraland (Virtual World Content API) MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Decentraland (Virtual World Content API) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Decentraland (Virtual World Content API) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Decentraland (Virtual World Content API) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Decentraland (Virtual World Content API) Agent",
            instructions="You have access to Decentraland (Virtual World Content API) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Decentraland. 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 Decentraland (Virtual World Content API) 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 Decentraland (Virtual World Content API) MCP in OpenAI Agents SDK

Install the package, define your server parameters using `MCPServerStreamableHttp`, and pass it to your Agent constructor. The MCP Server exposes fifteen available tools that the SDK automatically discovers at runtime.

Yes. Your agent calls `get_marketplace_catalog` with specified filters to parse the active item list. The SDK handles the argument passing directly, returning structured JSON to the model.

No. The Decentraland (Virtual World Content API) server exposes its schema directly to the SDK, which handles the tool definition parsing automatically. You avoid writing manual function calling JSON.

Your agent runs `get_realms` to fetch active server instances and their current user loads. It then queries `get_main_realm_about` to determine the best connection target.

The server processes transient authentication requests locally in ephemeral sandbox containers. It never stores your private keys or session tokens, passing them directly to Decentraland's decentralized identity endpoints.

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