How to Use the DOAJ MCP in OpenAI Agents SDK

Q: How do I register the DOAJ tools in my OpenAI Agents SDK pipeline?

Install openai-agents and initialize the server connection using MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass the server instance inside the mcpservers list when creating your agent, and set cacheToolsList=True to speed up tool discovery.

Q: What happens if my OpenAI Agents SDK agent tries to upload a massive batch of DOAJ articles?

The bulkcreatearticles tool requires batches to stay around 600KB to avoid timeouts. You should configure your agent's guardrails or system instructions to split large metadata payloads into smaller chunks before invoking the tool.

Q: How does the agent handle duplicate DOIs during article creation?

When the agent runs createarticle, any existing record with an identical DOI or full-text URL is automatically overwritten. If you want to modify a record without a full overwrite, have your agent use updatearticle instead.

Search open-access research and push metadata directly from OpenAI Agents SDK workflows using managed API endpoints.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DOAJ MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated curation with OpenAI Agents SDK guardrails

This MCP Server exposes `search_journals` and `create_application` so your agents can query academic databases and submit applications without manual intervention. The SDK automatically discovers these capabilities, letting your models check status fields like `admin.current_journal` before making changes. Since these operations write to a public directory, you need strict execution boundaries. The SDK lets you set pre-execution rules so your agent doesn't trigger `create_application` with malformed journal IDs. It's a clean way to keep academic metadata clean before it hits the live index.

Safe bulk metadata publishing

The `bulk_create_articles` tool lets your agent push batches of academic metadata up to 600KB directly to the directory. When your pipeline processes a new issue, the agent coordinates the payload size and structures the JSON to match Elasticsearch requirements. If a publication already exists, your agent uses `create_article` or `update_article` to overwrite or modify the records based on matching DOIs. The OpenAI dashboard gives you a full execution trace of these writes, so you can see exactly when a publisher API key was used.

Targeted literature discovery via elastic queries

Using `search_articles` with specific Elasticsearch queries like `bibjson.title:"Quantum"`, your agent narrows down academic sources without scraping raw web pages. This targeted fetching feeds clean, peer-reviewed data straight into your agent's context window. If your workflow requires checking specific papers, the agent invokes `get_article` using the unique DOAJ identifier. It bypasses broad web searches, keeping your agents focused on structured academic metadata.

Setup guide

Set up DOAJ 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 DOAJ tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and initialize the server connection using `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass the server instance inside the `mcp_servers` list when creating your agent, and set `cacheToolsList=True` to speed up tool discovery.

Yes, Vinkius manages your DOAJ publisher API key securely at the platform level, so your code never exposes it. Your agent simply calls tools like `create_article` or `delete_article` through the secure MCP connection.

The `bulk_create_articles` tool requires batches to stay around 600KB to avoid timeouts. You should configure your agent's guardrails or system instructions to split large metadata payloads into smaller chunks before invoking the tool.

When the agent runs `create_article`, any existing record with an identical DOI or full-text URL is automatically overwritten. If you want to modify a record without a full overwrite, have your agent use `update_article` instead.

Vinkius runs this MCP server inside an isolated, ephemeral V8 sandbox that destroys itself after execution. Your credentials and metadata payloads pass through secure, zero-trust endpoints without being logged or cached on 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