How to Use the Gradient AI (LLM API & Finetuning) MCP in OpenAI Agents SDK

Q: How does the agent select which foundational model to use?

The agent calls listmodels to check which base models are available in your workspace. It then selects the right model ID to pass to completemodel or createmodel dynamically.

Q: Where does Gradient AI (LLM API & Finetuning) store training files when using OpenAI Agents SDK?

Files uploaded via uploadfile go straight to the secure Gradient API. All data is isolated within your specific workspace token. Vinkius runs the MCP Server in an ephemeral sandbox, meaning your raw file contents are never stored on the hosting platform.

Deploy production-grade model tuning and RAG workflows using OpenAI Agents SDK with built-in safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gradient AI (LLM API & Finetuning) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Gradient AI (LLM API & Finetuning) 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 Gradient AI (LLM API & Finetuning) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fine-tune models on the fly

The `create_model` tool kicks off custom model instances directly inside your agentic loops. You upload training datasets using `upload_file` and run `fine_tune_model` to adapt models to your team's specific jargon. This MCP Server exposes these capabilities directly to your agent workflows. Once trained, your agent checks the status with `get_model` and runs predictions via `complete_model`. This lets your production agents adapt to new user data without manual developer intervention.

Process raw documents with the OpenAI Agents SDK

The `extract_pdf` tool pulls raw text out of complex PDF documents so your agent can process them. Your agent then feeds that raw output into `extract_entity` to pull clean, structured data that fits your exact schema. If you need to handle audio files instead, the MCP Server uses `create_transcription` and `get_transcription` to convert spoken words into text. This lets your agent run sentiment analysis with `analyze_sentiment` on any incoming customer call.

Run semantic searches with custom RAG

The `create_rag_collection` tool sets up vector databases for your agent to search through. Your agent converts raw text into vector representations using `generate_embeddings` before saving them to the collection. When a user asks a question, the agent uses `answer_question` to search the collection and return the right answer. This keeps your agent's knowledge grounded in your actual files instead of letting it make things up.

Setup guide

Set up Gradient AI (LLM API & Finetuning) 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 Gradient AI (LLM API & Finetuning) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Gradient AI (LLM API & Finetuning) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Gradient AI (LLM API & Finetuning) 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="Gradient AI (LLM API & Finetuning) Agent",
            instructions="You have access to Gradient AI (LLM API & Finetuning) 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 Gradient AI. 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 Gradient AI (LLM API & Finetuning) 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 Gradient AI (LLM API & Finetuning) MCP in OpenAI Agents SDK

Install the SDK package first. Then instantiate the client using the streamable HTTP transport class with your Vinkius endpoint. Pass the server instance directly into your Agent constructor to let it auto-discover tools.

Yes, you can run multiple jobs concurrently. Your agent calls `create_model` and `fine_tune_model` asynchronously, then tracks progress using `get_model` without blocking other agent workflows.

The agent calls `list_models` to check which base models are available in your workspace. It then selects the right model ID to pass to `complete_model` or `create_model` dynamically.

Set the tool list caching parameter to true in your SDK configuration. This prevents the agent from making repeated schema discovery requests, keeping latency low.

Files uploaded via `upload_file` go straight to the secure Gradient API. All data is isolated within your specific workspace token. Vinkius runs the MCP Server in an ephemeral sandbox, meaning your raw file contents are never stored on the hosting platform.

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