How to Use the Internet Archive Wayback MCP in Google ADK

Q: How do I set up the Internet Archive Wayback MCP Server with the Google ADK?

Instantiate McpToolset with the streamable HTTP server URL and pass it to your LlmAgent tools list. The SDK automatically registers all ten tools for your Gemini models.

Q: Can Gemini use the Internet Archive Wayback tools to count historical updates in Google ADK?

Yes, the agent can call getcapturecount to fetch the total number of preserved snapshots for any URL. This metric helps your system evaluate how frequently a target site changed.

Q: How do I find the oldest archive record for a web page?

Your agent should run getfirstcapture to get the earliest recorded snapshot. The tool returns the exact timestamp and original URL structure.

Connect Gemini to historical web data using Google ADK and the Internet Archive Wayback 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 Internet Archive Wayback MCP to Google ADK

Create your Vinkius account to connect Internet Archive Wayback 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 Internet Archive Wayback with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Wayback MCP Server data into Gemini's long context.

`get_cdx_captures` retrieves detailed capture histories for any URL, pulling raw metadata into your Google ADK agent. Because Gemini handles massive token counts, you can feed years of historical index data directly into a single reasoning step. To keep things clean, your agent calls `get_captures_collapsed` to remove duplicate snapshots. This keeps your BigQuery-linked pipelines focused on unique structural changes over time.

Isolate archived assets by response type.

`get_captures_by_mime_type` isolates specific file types like PDFs or images from the archive. Your Google ADK agent uses this tool to extract historical documents without downloading raw HTML. If you need to analyze server health patterns, `get_captures_by_status` filters snapshots by HTTP status codes. This lets your enterprise agent run diagnostic reports on historical downtime.

Map forgotten endpoints across your enterprise.

`get_subdomain_captures` maps every recorded subdomain of a target domain in one call. Your agent can run this tool to discover forgotten endpoints and historical assets. To check if a specific page is still available, the agent calls `check_availability`. This tool returns the closest snapshot timestamp, verifying if a resource remains preserved.

Setup guide

Set up Internet Archive Wayback 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 Internet Archive Wayback 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="Internet Archive Wayback_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Internet Archive Wayback 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 Internet Archive Wayback Machine. 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 Internet Archive Wayback 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 Internet Archive Wayback MCP in Google ADK

Instantiate `McpToolset` with the streamable HTTP server URL and pass it to your `LlmAgent` tools list. The SDK automatically registers all ten tools for your Gemini models.

Yes, the agent can call `get_capture_count` to fetch the total number of preserved snapshots for any URL. This metric helps your system evaluate how frequently a target site changed.

The Vinkius infrastructure hosts the server in an isolated sandbox, shielding your Google Cloud environment from external API latency. Your agent queries the tools via standard HTTP transport.

Your agent should run `get_first_capture` to get the earliest recorded snapshot. The tool returns the exact timestamp and original URL structure.

This setup only sends the requested target URLs and domain strings to the archive.org public endpoints. The MCP server runs inside an ephemeral, zero-trust sandbox, keeping your internal Google Cloud data and BigQuery tables private.

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