How to Use the Anyscale MCP in OpenAI Agents SDK

Directly manage your Anyscale infrastructure and LLM endpoints within your OpenAI Agents SDK production workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anyscale MCP to OpenAI Agents SDK

Create your Vinkius account to connect Anyscale 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 Anyscale with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage LLM endpoints in OpenAI Agents SDK

Trigger `chat_completion` or `text_completion` tools to route agent requests through Anyscale models. You get full control over the message stack and system roles without leaving your Python environment. Your agents parse these responses using the SDK's internal guardrails. This keeps your production logic tight and predictable.

Monitor Anyscale jobs with OpenAI Agents SDK

Use `list_jobs` and `list_services` to pull real-time data on your active training and inference deployments. It gives your agent a clear view of current cluster health. Tracking these metrics ensures your agent reacts to infrastructure state changes instantly. You avoid manual dashboard checks by letting the agent audit the status logs itself.

Vector integration for OpenAI Agents SDK

Call `generate_embeddings` to convert raw text into semantic vectors for RAG pipelines. Your agent handles the embedding generation directly before pushing data to your storage layer. This MCP server keeps your vectorization logic consistent across your agent fleet. You define the flow once and let the SDK handle the transport overhead.

Setup guide

Set up Anyscale 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 Anyscale tools at runtime.
3

Create your Agent

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

Run the agent

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

You instantiate an MCPServerStreamableHttp object with your endpoint URL. Pass this instance into the agent constructor's mcp_servers list to enable auto-discovery of tools.

Yes, because the SDK validates tool output against your defined schemas. Any data returned from Anyscale tools undergoes the same safety checks as your internal agent logic.

Absolutely. You treat the Anyscale tools as standard agent capabilities. The agent decides when to invoke the completion tools based on your prompt instructions.

The SDK catches the error and allows you to define a fallback or retry behavior. You handle the failure state in your standard agent error-handling blocks.

Your API keys and endpoint credentials stay local to your environment. We only touch the prompt text and model metadata required for the specific tool call.

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