How to Use the Unpaywall (Open Access Papers) MCP in LangChain

Q: How do I use Unpaywall (Open Access Papers) with LangChain?

You pass the getarticleoastatus tool definition to your agent's toolkit. The agent will then decide when and how to call it based on the user's prompt or intermediate results.

Build multi-step reasoning agents with LangChain, checking Open Access status for every DOI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unpaywall (Open Access Papers) MCP to LangChain

Create your Vinkius account to connect Unpaywall (Open Access Papers) to LangChain 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 Unpaywall (Open Access Papers) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Determine OA Status in a Chain

The agent uses the `get_article_oa_status` tool to check an article's open access standing based on a provided DOI. This function returns not just a simple yes/no, but detailed location data for full-text PDFs. This output feeds directly into the next step of your chain. For instance, one agent can gather several DOIs and pass them to the MCP Server, which returns structured metadata that another agent then uses to decide the best search strategy.

Process Multiple DOI Lookups

You can aggregate multiple scholarly identifiers and feed them into a single call to `get_article_oa_status`. The MCP Server handles these concurrent lookups, giving you structured results for each one. This mechanism lets your agent batch process information efficiently. Your AI client determines the correct tool input—a list of DOIs—and executes the lookup, saving time and steps in your reasoning pipeline.

Verify Scholarly Content Availability

Need to know if a paper is free? The `get_article_oa_status` tool verifies Open Access status using only a DOI. It provides the precise location and link type for the full-text article. This capability helps your agent filter down potential research sources before making expensive external API calls. You get actionable data on availability, not just general guesses.

Setup guide

Set up Unpaywall (Open Access Papers) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Unpaywall (Open Access Papers) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "unpaywall-open-access-papers-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Unpaywall (Open Access Papers) transactions"
    })
    print(result["messages"][-1].content)

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 Unpaywall. 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 Unpaywall (Open Access Papers) 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 Unpaywall (Open Access Papers) MCP in LangChain

You pass the `get_article_oa_status` tool definition to your agent's toolkit. The agent will then decide when and how to call it based on the user's prompt or intermediate results.

Yes, you can structure your input data to send a batch of DOIs through the MCP Server. The server processes them and returns the OA status for every identifier in that list.

The tool gives you structured metadata, including the Open Access status and specific URLs where the full-text PDF is located. This data structure makes it easy for your agent to consume and act upon.

Not really. You simply integrate the MCP Server client into your existing chain logic. The tool's output is designed to be consumed by subsequent steps in your reasoning flow.

This server handles scholarly article metadata, specifically the DOI and associated Open Access status records. Your agent works with these structured identifiers and link details.

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