How to Use the MIT DBLP MCP in Google ADK

Q: Can my Google ADK agent search for systems and database papers using MIT DBLP?

Yes, your agent invokes searchsystemspapers and searchdatabasepapers to query premier venues in those domains. These specialized tools return clean metadata that fits directly into your Google Cloud data pipelines. You get instant access to papers from OSDI, SOSP, VLDB, and SIGMOD.

Q: How do I fetch the full metadata of a specific paper?

Your agent calls getpublication using a unique key like 'conf/nips/VaswaniSPUJGKP17'. The server returns the title, full author list, year, and DOI. Your agent then uses this structured record to build clean citations.

Feed structured CS literature directly into your Google ADK pipelines for long-context Gemini reasoning.

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 Google ADK

Create your Vinkius account to connect MIT DBLP to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run deep academic search via Google ADK

`search_publications` queries more than six million computer science records to find exact paper matches. Your Google ADK agent processes this raw data inside its million-token context window to synthesize massive literature reviews. To keep your token usage efficient, you filter queries using `search_by_year` to target specific eras. The agent ingests clean JSON payloads directly, avoiding the overhead of scraping public web pages.

Trace research lineage with an MCP Server

`get_author` resolves a researcher's DBLP PID to fetch their verified profile. This MCP Server supplies your Google ADK agent with structured author records, allowing it to trace academic lineage across decades. Your pipeline then uses `get_coauthors` to map out the researcher's entire network of collaborators. The agent writes these relationships straight to BigQuery for downstream graph analysis.

Extract venue-specific data for Google ADK

`get_venue` pulls detailed metadata for conferences and journals using short abbreviations like ICML or OSDI. Your Google ADK tools use this data to categorize papers before sending them to your analysis pipeline. If you need the entire contents of a proceedings volume, `get_venue_publications` fetches every paper from that year. Your agent runs parallel classification on these papers using Vertex AI.

Setup guide

Set up MIT DBLP MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with MIT DBLP tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="MIT DBLP_agent",
    model="gemini-2.0-flash",
    instruction="You have access to MIT DBLP tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You initialize McpToolset with your Vinkius HTTP stream parameters and pass it to the LlmAgent constructor. The Gemini model automatically discovers all sixteen tools, including `search_ai_papers`. You can also use the tool_names parameter to expose only the specific search tools you need.

Yes, your agent invokes `search_systems_papers` and `search_database_papers` to query premier venues in those domains. These specialized tools return clean metadata that fits directly into your Google Cloud data pipelines. You get instant access to papers from OSDI, SOSP, VLDB, and SIGMOD.

The server runs in a secure sandbox on Vinkius, which buffers upstream requests to prevent rate-limit blocks. Your Google ADK agent can execute sequential calls like `get_author_publications` without triggering IP bans. This setup makes large-scale academic ingestion reliable.

Your agent calls `get_publication` using a unique key like 'conf/nips/VaswaniSPUJGKP17'. The server returns the title, full author list, year, and DOI. Your agent then uses this structured record to build clean citations.

Yes, because the server only processes public publication keys, author names, and venue abbreviations. Vinkius handles the connection using ephemeral containers, ensuring your search terms and research topics are never stored. Your Google Cloud security boundaries remain completely intact.

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