How to Use the CrossRef MCP in OpenAI Agents SDK

Build production-ready agents that query 140M+ scholarly works using the OpenAI Agents SDK and 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 CrossRef MCP to OpenAI Agents SDK

Create your Vinkius account to connect CrossRef 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve DOIs directly in your OpenAI Agents SDK pipeline

The `get_crossref_doi` tool pulls complete metadata for any scholarly work directly into your agent's context. You feed it a standard string like 10.1038/nature12373, and it returns the title, full author list, journal name, publication year, citation count, and abstract. This means your production system can verify references before generating text. Built-in guardrails validate the DOI lookup before execution, ensuring your agent only works with factual bibliographic data instead of hallucinating citations.

Search 140M+ academic papers across disciplines

Your agent uses the `search_crossref` tool to query the world's largest DOI registry. Every search result includes the exact DOI, current citation counts, and full bibliographic data for works across all scientific fields. Handoffs between specialized agents become much more effective when backed by real academic data. A research agent can run the search and pass the resolved citation metrics to a writing agent, all tracked visibly through your OpenAI dashboard.

Map researcher publication histories automatically

Calling the `search_crossref_author` tool returns a specific author's publications sorted by relevance. The response includes citation counts for each paper, letting your agent rank a researcher's most impactful work instantly. Because this MCP Server integrates with zero configuration, your agent auto-discovers the author search capability on startup. You just pass the server to the Agent constructor and let the system handle the API routing.

Setup guide

Set up CrossRef 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 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CrossRef 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 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 Agent",
            instructions="You have access to CrossRef 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 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 MCP in OpenAI Agents SDK

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your Vinkius endpoint URL and pass it to your Agent constructor as mcp_servers=[server]. The SDK auto-discovers the tools immediately.

Yes. You can set cacheToolsList=True when configuring the server connection. This improves performance when your agent makes repeated author lookups or DOI queries during a single session.

The SDK relies on its built-in guardrails to manage execution errors. If a requested DOI does not exist in the registry, the tool returns an error state that the agent catches and processes without breaking your production pipeline.

It provides a list of publications associated with the requested author name. Each item includes the title, DOI, publication year, and current citation count.

Your search queries and DOI lookups run through the Vinkius V8 Isolate Sandbox. The connection is ephemeral and zero-trust, meaning your specific academic interests and author queries disappear the moment the session ends.

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