How to Use the Writer (AI Enterprise LLM) MCP in OpenAI Agents SDK

Q: Can I manage my knowledge base structure with Writer (AI Enterprise LLM) and OpenAI Agents SDK?

Yep. You can create new data boundaries by calling creategraph, and you can view everything available using listgraphs. The server also gives you a list of all models it supports via the listmodels tool.

Q: What happens if an asynchronous job fails with Writer (AI Enterprise LLM) and OpenAI Agents SDK?

The agent can detect this using listapplicationjobs. If a job failed, it'll provide the retryapplicationjob tool. This lets your production system automatically attempt the task again without manual intervention.

Q: How does Writer (AI Enterprise LLM) interact with external data sources in OpenAI Agents SDK?

It's built around Knowledge Graphs and web search. You use websearch for real-time info, or you upload documents via uploadfile so the system can build a dedicated graph that answers questions using askquestion.

Build production agents with OpenAI Agents SDK. Get reliable answers and manage enterprise data using Writer (AI Enterprise LLM).

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Writer (AI Enterprise LLM) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Writer (AI Enterprise LLM) 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 Writer (AI Enterprise LLM) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Querying Knowledge Graphs

The `ask_question` tool lets your agent query specific, structured data sets stored in Knowledge Graphs. You can run complex retrieval-augmented generation (RAG) queries against multiple graphs simultaneously. Need to get started? First, use `create_graph` to set up a new graph structure. After that, upload the source material using `upload_file`, and your agent handles the rest of the querying process.

Generating Complex Content

When you need content, start with `text_completion` for simple prompts or use `chat_completion` for multi-turn conversation flows. If the content requires a full no-code application workflow, your agent can manage that using either `generate_application_content` (sync) or `generate_application_content_async` (awaiting job ID). For multilingual needs, don't forget the `translate_text` tool. It handles translations between supported languages so you never have to stitch together different API calls.

File and Data Management

The `add_file_to_graph` tool lets your agent ingest files, keeping your knowledge base current. If a file needs updating or removal, the agent can use `remove_file_from_graph` or permanently delete it with `delete_file`. You always know what you're working with because of `list_files`, which gives you a paginated view of everything uploaded. Want to analyze an image attached to a document? Use `analyze_vision` to get insights from visual data, whether it’s a photo or a scanned PDF.

Setup guide

Set up Writer (AI Enterprise LLM) 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 Writer (AI Enterprise LLM) tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent handles the workflow. You can chain tools together: first, use `web_search` to get current data; then, pass that result to a Knowledge Graph via `add_file_to_graph`; finally, ask questions using `ask_question`. The OpenAI Agents SDK manages all those handoffs.

Yep. You can create new data boundaries by calling `create_graph`, and you can view everything available using `list_graphs`. The server also gives you a list of all models it supports via the `list_models` tool.

The agent can detect this using `list_application_jobs`. If a job failed, it'll provide the `retry_application_job` tool. This lets your production system automatically attempt the task again without manual intervention.

It's built around Knowledge Graphs and web search. You use `web_search` for real-time info, or you upload documents via `upload_file` so the system can build a dedicated graph that answers questions using `ask_question`.

This server primarily deals with file metadata, uploaded binary content, and structured text data within Knowledge Graphs. All these assets must be managed carefully by your agent.

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