How to integrate Archive.org MCP with OpenAI Agents SDK

This guide walks you through connecting Archive.org to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Archive.org agent that can search collections, download item files, inspect wayback captures, fetch iiif manifests, and manage item metadata through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Archive.org account through Composio's Archive.org MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Archive.org logoArchive.org
Api Key

Archive.org is the Internet Archive's digital library of websites, books, audio, video, and images. Use it to preserve, explore, and access historical web captures and public-domain media.

26 Tools

Introduction

This guide walks you through connecting Archive.org to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Archive.org agent that can search collections, download item files, inspect wayback captures, fetch iiif manifests, and manage item metadata through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Archive.org account through Composio's Archive.org MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Archive.org with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Archive.org
  • Configure an AI agent that can use Archive.org as a tool
  • Run a live chat session where you can ask the agent to perform Archive.org operations

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Archive.org MCP server, and what's possible with it?

The Archive.org MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Archive.org account. It provides structured and secure access to archived content, Wayback captures, item records, usage analytics, and account tasks, so your agent can search collections, retrieve files, manage items, inspect activity, and handle reviews on your behalf.

  • Content search and retrieval: Have your agent search Archive.org by keywords and metadata, inspect complete item records, and download public files.
  • Wayback history research: Instruct your agent to find the closest archived version of a web page or list available captures for a website.
  • Item and file management: Direct your agent to check identifier availability, upload, copy, or delete files, update item metadata, and request new derivatives.
  • Images, manifests, and analytics: Let the agent inspect IIIF image details and manifests, render selected image regions, and review item views, history, geography, and referrers.
  • Account tasks and reviews: Have your agent check your account details, monitor catalog tasks and limits, read task logs, and create, update, retrieve, or delete your reviews.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Archive.org project
  • Some knowledge of Python or Typescript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Archive.org.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for Archive.org
const session = await composio.create(userId as string, {
  toolkits: ['archive_org'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only archive_org.
  • The router checks the user's Archive.org connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Archive.org.
  • This approach keeps things lightweight and lets the agent request Archive.org tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access Archive.org. Help users perform Archive.org operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Archive.org and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute Archive.org operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

// Simple CLI
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: 'You: ',
});

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize Archive.org.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Archive.org and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['archive_org'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access Archive.org. Help users perform Archive.org operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

  // Simple CLI
  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: ',
  });

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating Archive.org MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Archive.org.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

Every Archive.org action and event your agent gets out of the box.

Advanced Search Archive.org Items

Search Archive.

Check Identifier Availability

Check whether an Archive.

Check Archive.org Upload Limit

Check whether Archive.

Copy Item File

Copy one Archive.

Delete Item File

Submit asynchronous deletion of one named file from an Archive.

Delete My Archive.org Review

Permanently delete the connected Archive.

Derive Archive.org Item

Queue Archive.

Download Item File

Download one public file from an Archive.

Find Wayback Snapshots

Find the closest archived Wayback Machine snapshot for each requested URL, using one before, after, or either direction for the batch.

Get Connected Archive.org User

Return the authenticated Archive.

Get Detailed Archive.org Views

Get bounded geographic view analytics and, for items, top referrers over a recent window or date range.

Get IIIF Image Info

Get normalized IIIF Image API capabilities through Archive.

Get IIIF Manifest

Get a compact IIIF Presentation manifest for an Archive.

Get Item Metadata

Get an Archive.

Get Item View Counts

Get all-time, last-30-day, and last-7-day view counts for one or more Archive.

Get Item View History

Get a bounded daily view history for one Archive.

Get My Review

Get the connected Archive.

Get Archive.org Task Log

Download a plain-text log for a task visible to the connected account.

Get Task Rate Limits

Report the connected account's current task capacity and in-flight counts for one Archive.

List Archive.org Tasks

Return any documented combination of the connected account's task summary, active catalog, and resource-authorized history, one page at a time.

List Wayback Captures

Return one bounded structured CDX page of Wayback captures for a URL or host.

Render IIIF Image

Render a bounded crop, resize, rotation, quality, and format from a fixed Archive.

Search Archive.org Items

Search Archive.

Update Item Metadata

Apply JSON Patch changes to one Archive.

Upload Item File

Create or replace one file through Archive.

Upsert My Archive.org Review

Create or overwrite the connected Archive.

FAQ

Frequently asked questions

With a standalone Archive.org MCP server, the agents and LLMs can only access a fixed set of Archive.org tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Archive.org and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Archive.org tools.

Yes, absolutely. You can configure which Archive.org scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Archive.org data and credentials are handled as safely as possible.

Start with Archive.org.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Archive.org tool your agent needs.Free to start.

Start building