How to Use the Internet Archive MCP in AutoGen

Q: How do AutoGen agents collaborate using the Internet Archive tools?

One agent can run searchbydaterange to find historical files, while a second agent calls getitemmetadata to verify the publisher. They share this metadata in their conversation thread to reach a consensus.

Q: How do I configure this Internet Archive MCP integration in AutoGen?

Use the mcpservertools helper with our hosted HTTP endpoint URL. Pass the resulting tool list directly into your AssistantAgent constructor to give your agents instant archive access.

Q: Can my agents search for specific media formats like vintage software?

Yes, your agents can use searchbymediatype to target software, audio, or images. This allows specialized agents to focus only on the formats they are designed to process.

Equip your AutoGen agent teams to debate, verify, and retrieve millions of historical records.

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 MCP to AutoGen

Create your Vinkius account to connect Internet Archive 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 Internet Archive with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Give your AutoGen agents a shared historical memory

By running the `search` tool, your AutoGen agent teams can access objective historical sources to resolve complex debates. This MCP Server lets one agent pull historical facts while a critic agent validates the sources. Our consensus-driven approach ensures your agents do not hallucinate historical timelines. When an agent needs to back up an argument, it calls `get_item_metadata` to inspect publication dates and creators. This structures the debate around hard, verified data, allowing your AutoGen team to write highly accurate reports.

Automate link verification and historical recovery

By calling the `wayback_availability` tool, an AutoGen recovery agent can find the last working snapshot of any dead reference. This MCP integration lets your agents negotiate the best archive version to use and update your system records without manual intervention. This collaborative workflow ensures your agents can access historical web pages even if the original sites are gone. It adds a layer of operational resilience to your automated web research pipelines.

Filter and audit public datasets collaboratively

By using the `search_by_collection` tool, AutoGen agents can divide and conquer large archives. One agent can run the search to pull a batch of records, while another calls `get_views_stats` and `get_item_reviews` to audit their quality. Once they agree on the best assets, a third agent uses `get_item_files` to retrieve the files. This structured division of labor makes processing massive public datasets incredibly efficient and reliable.

Setup guide

Set up Internet Archive 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 Internet Archive 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="Internet Archive_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Internet Archive 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="Internet Archive_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Internet Archive 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 Internet Archive. 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 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 MCP in AutoGen

One agent can run `search_by_date_range` to find historical files, while a second agent calls `get_item_metadata` to verify the publisher. They share this metadata in their conversation thread to reach a consensus.

Yes, you can pass a filtered list of tools from the MCP server to specific agents. For example, you can give your research agent `search` capabilities while restricting your archiver agent to `get_item_files`.

Use the `mcp_server_tools` helper with our hosted HTTP endpoint URL. Pass the resulting tool list directly into your `AssistantAgent` constructor to give your agents instant archive access.

Yes, your agents can use `search_by_mediatype` to target software, audio, or images. This allows specialized agents to focus only on the formats they are designed to process.

The server only handles public URLs, search queries, and archive identifiers. All data is processed in a secure, ephemeral V8 sandbox that wipes your session data immediately after execution, keeping your multi-agent conversation logs completely private from the MCP host.

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