How to Use the MIT DBLP MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK pipeline search for AI papers using MIT DBLP?

Yes, your agent calls searchaipapers to query top-tier machine learning venues directly. This tool returns structured metadata that maps perfectly to your agent's function-calling schema. You won't need to write custom parsing code for conferences like ICML or NeurIPS.

Q: How do I find an author's unique PID?

Your agent uses searchauthors to find the correct profile URL and disambiguation notes. Once it gets the PID, it passes that string to getauthor to fetch the complete profile. This two-step lookup ensures you never query the wrong researcher.

Feed clean CS publication data directly to your OpenAI Agents SDK pipelines without scraping or parsing HTML.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MIT DBLP MCP to OpenAI Agents SDK

Create your Vinkius account to connect MIT DBLP 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 MIT DBLP with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map academic networks with OpenAI Agents SDK

`get_coauthors` retrieves a ranked list of collaborators directly from the DBLP registry to map out research clusters. Your agent uses this raw node data to build real-time collaboration graphs without hitting rate limits or parsing HTML. You pass these nodes straight into OpenAI's structured outputs. Combined with `get_author_stats`, your agent evaluates a researcher's output over time and flags top-tier venue counts instantly.

Target specific computer science venues

`get_venue_publications` pulls all papers from a specific conference edition like NeurIPS or SIGMOD. The OpenAI Agents SDK maps these titles directly to agent memory, allowing automated literature reviews across thousands of records. By chaining `search_in_venue`, you filter the noise immediately to isolate specific sub-topics. Your agent handles the sequential calls under the hood, ensuring your pipeline only processes highly relevant papers.

Verify records with this MCP Server

`get_publication` fetches precise metadata for any specific paper using its unique DBLP key. This MCP Server gives your OpenAI Agents SDK the exact DOI and author list, preventing the model from hallucinating citations in generated reports. When your agent needs to find the correct key first, `search_publications` scans over six million records. The server returns clean JSON that your guardrails validate before executing the next step in your run.

Setup guide

Set up MIT DBLP 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 MIT DBLP tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package via pip, then initialize the MCPServerStreamableHttp instance using your Vinkius endpoint URL. Pass this server object in the mcp_servers list when constructing your agent. Enabling the cacheToolsList parameter ensures fast tool discovery during runtime.

Yes, your agent calls `search_ai_papers` to query top-tier machine learning venues directly. This tool returns structured metadata that maps perfectly to your agent's function-calling schema. You won't need to write custom parsing code for conferences like ICML or NeurIPS.

The Vinkius-hosted server manages upstream requests to DBLP to stay within their strict limits. Your agent executes `get_author_publications` safely because the MCP layer buffers and handles the connection pool. This prevents your local IP from getting blocked during deep recursive searches.

Your agent uses `search_authors` to find the correct profile URL and disambiguation notes. Once it gets the PID, it passes that string to `get_author` to fetch the complete profile. This two-step lookup ensures you never query the wrong researcher.

No, this server only transmits public academic metadata, author PIDs, and publication keys. Vinkius runs the server in an isolated sandbox, meaning your search queries and agent prompts never leak to the public DBLP directory. Your proprietary logic remains completely inside your local OpenAI environment.

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