How to Use the CrossRef Alternative MCP in OpenAI Agents SDK

Q: How do OpenAI Agents SDK handoffs handle CrossRef Alternative metadata?

One agent can search for papers using searchworks and hand the DOIs to a validation agent. The validation agent then calls getwork within the same OpenAI Agents SDK session.

Get 150M+ academic records directly inside your production OpenAI Agents SDK pipelines with zero-config tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CrossRef Alternative MCP to OpenAI Agents SDK

Create your Vinkius account to connect CrossRef Alternative 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 CrossRef Alternative with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run secure DOI metadata lookups in OpenAI Agents SDK

Exposing `get_work` and `get_works_by_doi_list` directly to your OpenAI Agents SDK runtime ensures your system pulls verified abstracts, author lists, and citation counts straight from CrossRef Alternative. The built-in guardrails in your OpenAI Agents SDK validate these incoming academic payloads before they hit your model, keeping your production pipelines clean. When your agent needs to resolve a long list of DOIs, it runs `get_works_by_doi_list` to fetch bulk CrossRef Alternative metadata in one turn, keeping your OpenAI dashboard traces neat and preventing token bloat.

Coordinate multi-agent funding audits using this MCP Server

Calling `search_funders` and `get_funder` allows your specialized OpenAI Agents SDK compliance agent to focus solely on tracking where research money comes from. It maps out funding sources, country codes, and total work counts without needing custom API integrations. This handoff works because the MCP Server exposes structured schemas that the OpenAI Agents SDK understands natively. If a funder's URI or location info is missing from CrossRef Alternative, the agent catches it early, logging the exact issue to your OpenAI dashboard before executing subsequent steps.

Filter academic publishers and journals on the fly

Using `search_journals` and `get_journal` lets you build research tools in OpenAI Agents SDK that sort the signal from the noise. Your agent verifies if a paper belongs to a reputable publication, filtering out predatory sources instantly using work counts and publisher metadata returned by `get_publisher`. You don't have to write custom validation logic for these CrossRef Alternative lookups. The OpenAI Agents SDK auto-discovers these tools, allowing your agent to dynamically decide when to run `get_licenses` or `get_types` to narrow down its search parameters.

Setup guide

Set up CrossRef Alternative 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 CrossRef Alternative tools at runtime.
3

Create your Agent

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

Run the agent

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

It connects via a single streamable HTTP endpoint. Your OpenAI Agents SDK auto-discovers all 13 tools, including `search_works` and `get_work`, without needing manual MCP configuration.

Yes, you can filter the tool list during initialization in your OpenAI Agents SDK setup. If you only want your agent to read papers, expose `get_work` and hide write-heavy or administrative tools.

One agent can search for papers using `search_works` and hand the DOIs to a validation agent. The validation agent then calls `get_work` within the same OpenAI Agents SDK session.

Writing scrapers is a fragile mess. This MCP Server gives your OpenAI Agents SDK agent structured, ready-to-use JSON for 150M+ works, saving you from parsing messy HTML.

Vinkius isolates this server in a zero-trust V8 sandbox. Your DOIs, funder names, and journal search queries are never stored or used to train OpenAI models.

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