How to Use the dYdX (Decentralized Perpetual Exchange API) MCP in OpenAI Agents SDK

Q: How do I connect the dYdX (Decentralized Perpetual Exchange API) MCP Server to OpenAI Agents SDK?

Install the package with pip install openai-agents. Use the MCPServerStreamableHttp class to point to the Vinkius endpoint, and pass it directly into your Agent's mcpservers list. The SDK handles tool discovery automatically.

Q: What is the fastest way to check open positions?

Have your agent call v4listpositions. This tool returns all open risk profiles, allowing your agent to make immediate execution decisions.

Build production trading agents that execute dYdX v4 orders with built-in safety guardrails using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect dYdX (Decentralized Perpetual Exchange API) MCP to OpenAI Agents SDK

Create your Vinkius account to connect dYdX (Decentralized Perpetual Exchange 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 dYdX (Decentralized Perpetual Exchange API) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe order execution with OpenAI Agents SDK

Your OpenAI Agents SDK agent can now execute high-speed dYdX perpetual trades directly. By giving your OpenAI Agents SDK access to this MCP Server, it can run `v4_create_order` or `v4_cancel_order` based on real-time market changes. You get built-in OpenAI guardrails to validate these financial transactions before they hit the dYdX chain. The agent checks current market depth with `v4_get_orderbook` and verifies account exposure through `v4_list_positions` before pulling the trigger, keeping your risk capped.

Multi-agent market analysis and execution

Split your dYdX trading strategy into specialized OpenAI agents that hand off tasks to one another. One agent can monitor price trends with `v4_get_candles` and `v4_get_stats`, then hand off the execution phase to a dedicated trading agent. This delegation keeps your dYdX execution clean within the OpenAI Agents SDK framework. The executing agent calls `v4_list_fills` to confirm the trade went through, while the monitoring agent continues to track the L2 book via `v4_get_orderbook` for the next entry point.

Direct account state tracking in production

Keep your production OpenAI trading systems updated with actual on-chain dYdX states. Your agent queries `v4_get_account` to monitor balances, equity, and active margin requirements without relying on slow external webhooks. The OpenAI Agents SDK handles the underlying MCP connection over secure HTTP streams. This lets your agent run continuous loops, checking `v4_list_orders` to manage open limit orders on dYdX instantly.

Setup guide

Set up dYdX (Decentralized Perpetual Exchange 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 dYdX (Decentralized Perpetual Exchange API) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives dYdX (Decentralized Perpetual Exchange 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 dYdX (Decentralized Perpetual Exchange 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="dYdX (Decentralized Perpetual Exchange API) Agent",
            instructions="You have access to dYdX (Decentralized Perpetual Exchange 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 dYdX. 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 dYdX (Decentralized Perpetual Exchange 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 dYdX (Decentralized Perpetual Exchange API) MCP in OpenAI Agents SDK

Install the package with `pip install openai-agents`. Use the `MCPServerStreamableHttp` class to point to the Vinkius endpoint, and pass it directly into your Agent's `mcp_servers` list. The SDK handles tool discovery automatically.

Yes, this toolset supports both protocols. Your agent can query v3 markets with `v3_list_markets` or execute v4 trades via `v4_create_order` depending on which market parameters it detects.

The SDK relies on standard HTTP backoff patterns. If your agent hits a rate limit while fetching `v4_get_orderbook` or executing `v4_create_order`, the connection manager handles the retries based on your configured policies.

Have your agent call `v4_list_positions`. This tool returns all open risk profiles, allowing your agent to make immediate execution decisions.

Vinkius runs this toolset in an isolated V8 sandbox. Your private keys and collateral addresses are injected as environment variables at runtime, meaning your OpenAI agent never exposes them to the public internet or logs them to the OpenAI dashboard.

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