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

Q: How do I use Unpaywall (Open Access Papers) in AutoGen?

You pass the getarticleoastatus tool to your AssistantAgent constructor. This makes the OA status check available as a resource that agents can call and debate over.

Force agents to debate OA status decisions using AutoGen with Unpaywall (Open Access Papers).

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate Article Availability

You set up multiple agents—say, a 'Research Agent' and a 'Compliance Agent.' The Research Agent uses `get_article_oa_status` to check OA status. The Compliance Agent then debates whether the retrieved links meet internal usage policy. This forces consensus-driven decision making where the final answer isn't obvious but requires deliberation between competing perspectives.

Structured Debate on DOIs

The MCP Server provides structured data via `get_article_oa_status` when given a DOI. This precise, verifiable output gives the agents objective facts to argue over. One agent might focus purely on speed (checking 10 DOIs quickly), while another focuses on completeness (ensuring all link types are checked).

Multi-Perspective Source Validation

Build systems where the answer requires input from multiple sources. Use `get_article_oa_status` to validate open access status, then have a separate agent challenge that finding against other known academic databases. It's about consensus: getting agreement on whether an article is truly accessible before proceeding with the workflow.

Setup guide

Set up Unpaywall (Open Access Papers) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Unpaywall (Open Access Papers) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Unpaywall (Open Access Papers)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Unpaywall (Open Access Papers) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Unpaywall (Open Access Papers)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Unpaywall (Open Access Papers) data")
    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 AutoGen

You pass the `get_article_oa_status` tool to your AssistantAgent constructor. This makes the OA status check available as a resource that agents can call and debate over.

Yes. You'll define roles—one agent might manage the input DOIs while another executes the `get_article_oa_status` tool call, ensuring a structured dialogue.

The tool provides structured metadata: Open Access status and specific PDF link locations. This verifiable data forms the core evidence that your competing agents must deliberate over.

Definitely. By grounding the discussion in real API results, you move past theoretical arguments and into decision-making based on verifiable scholarly data.

This server handles scholarly article metadata. You're working with DOIs, Open Access status indicators, and structured URL links to full-text PDFs.

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