How to Use the MIT DBLP MCP in AutoGen

Q: How do I register the MIT DBLP MCP Server tools in AutoGen?

You use the mcpservertools helper with your server's URL to retrieve the tools. Then, pass the resulting list to your AutoGen AssistantAgent constructor, which allows agents to call tools like searchauthors during conversations.

Q: Can AutoGen agents call MIT DBLP tools during a group chat?

Yes, any agent in the AutoGen group can invoke tools like getvenuepublications if they have been granted access. The coordinator agent manages which tool to call based on the current state of the debate.

Q: How do AutoGen agents handle author disambiguation on MIT DBLP?

The AutoGen agents can resolve ambiguities by calling searchauthors to view the disambiguation notes. Once they identify the correct PID, they pass it to getauthor to ensure they are analyzing the correct researcher.

Let AutoGen agents debate and analyze computer science research using the MIT DBLP MCP Server.

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 AutoGen

Create your Vinkius account to connect MIT DBLP 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 MIT DBLP with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent academic analysis in AutoGen

By calling `get_author_stats`, an AutoGen analyst agent can pull a researcher's metrics and share them in a multi-agent debate. Within the AutoGen framework, an analyst agent can use `get_author_stats` to pull a researcher's metrics, while a skeptical agent calls `get_coauthors` to verify who they actually publish with. The AutoGen agents collaborate to build a complete picture of an academic's impact. This collaborative AutoGen workflow ensures thorough analysis. By using `get_author_publications`, the AutoGen agents can review a researcher's recent output, arguing over the quality of the venues and identifying key trends in their work without human intervention.

Verify academic claims with this MCP Server

The `get_publication` tool prevents your AutoGen multi-agent system from relying on outdated knowledge during their discussions. When an AutoGen agent makes a claim about a paper, a verification agent can call `get_publication` to pull the exact metadata. It checks the title, year, and venue, forcing the AutoGen group to align their discussion with verified facts. If the AutoGen team needs to track down a specific paper, they can use `search_publications` or `search_by_year` to find the correct record. This structured verification loop keeps the entire AutoGen conversation grounded in real-world computer science data.

Domain-specific research sweeps using AutoGen

Using `search_theory_papers` allows specialized AutoGen agents to monitor different computer science fields independently. An AutoGen theory agent can use `search_theory_papers`, while a systems agent runs `search_systems_papers` to track new developments. They can then share their findings in a shared AutoGen group chat to identify cross-disciplinary breakthroughs. For targeted searches, the AutoGen agents can use `search_in_venue` to scan specific conferences like NeurIPS or SIGMOD. The McpToolAdapter handles the schema conversion, so your AutoGen agents can call these tools without any manual formatting overhead.

Setup guide

Set up MIT DBLP 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 MIT DBLP 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="MIT DBLP_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent MIT DBLP 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="MIT DBLP_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent MIT DBLP 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 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 AutoGen

You use the `mcp_server_tools` helper with your server's URL to retrieve the tools. Then, pass the resulting list to your AutoGen AssistantAgent constructor, which allows agents to call tools like `search_authors` during conversations.

Yes, any agent in the AutoGen group can invoke tools like `get_venue_publications` if they have been granted access. The coordinator agent manages which tool to call based on the current state of the debate.

The AutoGen agents can resolve ambiguities by calling `search_authors` to view the disambiguation notes. Once they identify the correct PID, they pass it to `get_author` to ensure they are analyzing the correct researcher.

Yes, you can filter the tools returned by the server before passing them to the AutoGen agent. For example, you can restrict a research agent to only use `search_ai_papers` to keep its focus entirely on machine learning.

Your search queries are safe. The server only handles public academic publication metadata and executes queries within a zero-trust, ephemeral sandbox. Your search queries and AutoGen agent conversations are never logged, cached, or exposed to the public.

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