How to Use the Alpaca Trading MCP in OpenAI Agents SDK

Q: How do I connect Alpaca Trading to the OpenAI Agents SDK?

Pass the Vinkius endpoint using MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="...")). Wrap it in an async context manager and hand it to your Agent constructor via the mcpservers argument.

Q: Can OpenAI Agents SDK track my Alpaca Trading order history?

It reads the data by calling getorders. You get a list of all open and closed positions, which the agent can then analyze to calculate your current risk exposure.

Q: What happens if I want to cancel everything at once?

Triggering deleteallorders sends a mass cancellation request to the exchange. The server returns a 207 Multi-Status code, telling your agent exactly which orders closed and which ones failed.

Build production-grade trading agents with OpenAI Agents SDK that execute real market orders through Alpaca.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Alpaca Trading MCP to OpenAI Agents SDK

Create your Vinkius account to connect Alpaca Trading 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 Alpaca Trading with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream real-time quotes to OpenAI Agents SDK

Calling `get_latest_stocks_quotes` feeds live market pricing straight into your agent's context window. You pass the ticker symbol, and the agent reads the current bid and ask spreads before making financial decisions. Since you are building with this specific SDK, those pricing checks show up directly in your OpenAI dashboard traces. You see exactly when the model requested the quote and how it reasoned about the spread before moving forward.

Execute trades with strict guardrails

The `create_order` tool pushes buy and sell requests to your Alpaca account. Your agent specifies the asset, quantity, and order type based on the market conditions it just observed. Production systems need safety nets. Before the agent fires off that market order, the built-in SDK guardrails validate the action. You define the constraints, ensuring a rogue prompt doesn't liquidate your portfolio by accident.

Manage broker accounts via this MCP Server

Using `create_broker_account` lets your multi-agent setup provision entirely new trading identities. The tool requires contact info, identity verification, and signed agreements to open the account. Handoffs between specialized agents work perfectly here. One agent handles the KYC document collection, while a secondary execution agent uses `update_account_configs` to set margin rules on the newly created profile.

Setup guide

Set up Alpaca Trading 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 Alpaca Trading tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Alpaca Trading tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Alpaca Trading 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="Alpaca Trading Agent",
            instructions="You have access to Alpaca Trading 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 Alpaca. 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 Alpaca Trading 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 Alpaca Trading MCP in OpenAI Agents SDK

Pass the Vinkius endpoint using `MCPServerStreamableHttp(params=MCPServerStreamableHttpParams(url="..."))`. Wrap it in an async context manager and hand it to your Agent constructor via the `mcp_servers` argument.

Yes. The SDK auto-discovers every tool from the connected MCP Server. Set `cacheToolsList=True` in your configuration to speed up initialization times.

It reads the data by calling `get_orders`. You get a list of all open and closed positions, which the agent can then analyze to calculate your current risk exposure.

Triggering `delete_all_orders` sends a mass cancellation request to the exchange. The server returns a 207 Multi-Status code, telling your agent exactly which orders closed and which ones failed.

Brokerage agreements and identity verification objects flow through an ephemeral V8 Isolate Sandbox. Vinkius drops the container the moment your session ends, meaning your KYC documents never touch a persistent 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