How to Use the Library of Congress MCP in Google ADK

Q: Can my Google ADK agent export Library of Congress metadata directly into BigQuery?

Yes, your Google ADK agent can call getitem to retrieve Library of Congress bibliographic metadata and format it as JSON. You can then load this structured Library of Congress data directly into your BigQuery tables using native Google ADK integrations.

Q: How does the Google ADK handle large image payloads from the Library of Congress?

The Google ADK agent uses getimageinfo to retrieve technical IIIF metadata instead of downloading giant binary files from the Library of Congress. This keeps your Google ADK agent lightweight while providing the exact Library of Congress image dimensions needed for downstream processing.

Q: Can I restrict which Library of Congress tools are exposed to my Google ADK agent?

Yes, you can use the toolnames filter parameter when initializing your McpToolset to expose only specific Library of Congress tools to your Google ADK agent. This prevents the Google ADK agent from executing unnecessary Library of Congress queries.

Connect millions of historical records to your Gemini-powered Google ADK agents using our managed 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 Library of Congress MCP to Google ADK

Create your Vinkius account to connect Library of Congress 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 Library of Congress with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map out entire archives with the Google ADK.

The `list_collections` tool lists all digital collections available in the Library of Congress, giving your Google ADK agent a starting point for deep historical research. Your Google ADK agent pulls these structured Library of Congress identifiers to map out the entire archive before running deeper queries. Once your Google ADK agent selects a collection, it uses `get_collection_items` to pull every single Library of Congress item record within that boundary. This structured index feed plugs directly into your BigQuery pipeline via Google ADK for long-term storage and analysis.

Target specific media formats using this MCP Server.

The `search` tool searches the entire Library of Congress website using raw keyword queries initiated by your Google ADK agent. Your Google ADK agent uses its long-context window to ingest these Library of Congress search results and identify key historical patterns. To optimize token usage, your Google ADK agent uses the `search_format` tool to filter these Library of Congress queries by specific formats like photos or manuscripts. This ensures your Google ADK agent only processes the precise Library of Congress data types your enterprise workflow requires.

Reconstruct historical documents in Google ADK.

The `get_resource` tool retrieves discrete digitized files, such as a specific page of a historical newspaper, using a unique resource identifier passed by your Google ADK agent to the Library of Congress. This gives your Google ADK agent direct access to raw Library of Congress archival assets. Your Google ADK agent then calls `get_text_service` to pull the underlying Library of Congress OCR text and word coordinates. This allows your Google ADK agent to perform precise spatial reasoning over the original Library of Congress page layout.

Setup guide

Set up Library of Congress 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 Library of Congress 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="Library of Congress_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Library of Congress 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 Library of Congress. 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 Library of Congress 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 Library of Congress MCP in Google ADK

Instantiate McpToolset with the StreamableHttpServerParameters pointing to your Vinkius URL, then pass it to the Google ADK LlmAgent constructor. This exposes all 8 Library of Congress archival tools directly to your Google ADK agent.

Yes, your Google ADK agent can call `get_item` to retrieve Library of Congress bibliographic metadata and format it as JSON. You can then load this structured Library of Congress data directly into your BigQuery tables using native Google ADK integrations.

The Google ADK agent uses `get_image_info` to retrieve technical IIIF metadata instead of downloading giant binary files from the Library of Congress. This keeps your Google ADK agent lightweight while providing the exact Library of Congress image dimensions needed for downstream processing.

Yes, you can use the tool_names filter parameter when initializing your McpToolset to expose only specific Library of Congress tools to your Google ADK agent. This prevents the Google ADK agent from executing unnecessary Library of Congress queries.

All Library of Congress queries, bibliographic records, and OCR text requests run inside a zero-trust V8 sandbox managed by Vinkius for your Google ADK agent. Vinkius secures the connection with single-token authentication, ensuring your proprietary Google ADK research parameters never leak to external networks.

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