How to Use the Internet Archive Wayback MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system filter snapshots by response type using the Internet Archive Wayback?

Yes, your agent can invoke getcapturesbymimetype to isolate specific assets like PDFs or HTML pages. You can also target specific server responses using getcapturesbystatus.

Q: Can I track when a specific URL was first archived?

Use getfirstcapture to retrieve the oldest recorded snapshot timestamp. The agent receives the exact date, status code, and original URL in a structured payload.

Give your OpenAI Agents SDK production agents direct access to historical web snapshots via the Internet Archive Wayback.

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 OpenAI Agents SDK

Create your Vinkius account to connect Internet Archive Wayback 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 Internet Archive Wayback with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stop guessing if historical links are actually dead.

`check_availability` checks if a URL has an active archive record and gets its closest snapshot. Your OpenAI Agents SDK agent runs this tool automatically when it encounters broken links or needs to audit external citations in real time. By executing `get_latest_capture`, the agent pulls the most recent archived version of the target page. This prevents your production pipelines from failing when live websites go offline.

Map an entire domain's historical graveyard.

`get_subdomain_captures` exposes the entire archived footprint of any target domain. Your agent parses this structured output to discover decommissioned subdomains and historical endpoints. To analyze how a site evolved over years, the agent runs `get_captures_by_year` with a four-digit year. This lets your system run historical audits without manual scraping.

Query raw CDX history with your MCP Server.

`get_cdx_captures` pulls raw historical metadata including file sizes, MIME types, and status codes. The OpenAI Agents SDK handles the tool discovery automatically, feeding this structured dataset straight into your agent's context window. Filtering results is straightforward. The agent invokes `get_captures_collapsed` to strip out redundant snapshots, keeping your token usage low and your context clean.

Setup guide

Set up Internet Archive Wayback 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 Internet Archive Wayback tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Internet Archive Wayback 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="Internet Archive Wayback Agent",
            instructions="You have access to Internet Archive Wayback 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 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 OpenAI Agents SDK

To query historical archives, install the package via pip and pass the server URL to the `MCPServerStreamableHttp` constructor. Your agents will auto-discover the tools and register them instantly.

Yes, your agent can invoke `get_captures_by_mime_type` to isolate specific assets like PDFs or HTML pages. You can also target specific server responses using `get_captures_by_status`.

The underlying server manages API requests to archive.org directly. If you hit rate limits, the server returns clean error states that your python agent can handle gracefully.

Use `get_first_capture` to retrieve the oldest recorded snapshot timestamp. The agent receives the exact date, status code, and original URL in a structured payload.

This server only transmits the target URLs and domain names you query to the public Wayback API. The MCP server runs in an isolated Vinkius sandbox, ensuring your system prompts and custom Python logic are never exposed.

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