Internet Archive MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Internet Archive through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Internet Archive "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in Internet Archive?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Internet Archive MCP Server
Connect the Internet Archive to any AI agent and access the world's largest digital library — 40M+ books, videos, audio recordings, software, images, and archived web pages — plus the Wayback Machine for historical website snapshots, all through natural conversation.
Pydantic AI validates every Internet Archive tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Universal Search — Search across the entire Internet Archive collection for books, films, music, software, images, and web pages with complex query syntax
- Collection Browsing — Explore curated collections like Prelinger Archives, Project Gutenberg, NASA images, TV news, and more
- Media Type Filtering — Search specifically for texts, movies, audio, software, images, or datasets
- Creator Search — Find all works by a specific author, director, musician, or organization
- Historical Date Range — Discover content from specific decades or year ranges
- Item Metadata — Get complete details for any item including description, subjects, collections, file formats, and download links
- File Listings — See all downloadable files for an item with formats (PDF, EPUB, MP4, MP3) and sizes
- User Reviews — Read community reviews and ratings for archived items
- Wayback Machine — Check if any URL has been archived and find the closest snapshot date
- View Statistics — Track popularity and access counts for archived items
The Internet Archive MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Internet Archive to Pydantic AI via MCP
Follow these steps to integrate the Internet Archive MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 10 tools from Internet Archive with type-safe schemas
Why Use Pydantic AI with the Internet Archive MCP Server
Pydantic AI provides unique advantages when paired with Internet Archive through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Internet Archive integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Internet Archive connection logic from agent behavior for testable, maintainable code
Internet Archive + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Internet Archive MCP Server delivers measurable value.
Type-safe data pipelines: query Internet Archive with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Internet Archive tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Internet Archive and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Internet Archive responses and write comprehensive agent tests
Internet Archive MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect Internet Archive to Pydantic AI via MCP:
get_item_files
Items may contain multiple files in various formats (PDF, EPUB, MP4, MP3, JPEG, etc.). The identifier is the unique item ID from search results or the item URL. Use this to see what formats are available for download. Files can be downloaded from: https://archive.org/download/{identifier}/{filename} Get the file listing for a specific Internet Archive item
get_item_metadata
Returns: title, creator, date, description, subjects, collection(s), publisher, language, license, download stats, reviews, and complete file listing with formats and sizes. The identifier is obtained from search results or can be found in the item URL (e.g., from https://archive.org/details/big_buck_bunny, the identifier is "big_buck_bunny"). Use this to get comprehensive information about a specific item before downloading or citing it. Get complete metadata and details for a specific Internet Archive item
get_item_reviews
Each review includes reviewer name, star rating, review text, and submission date. Use this to understand community reception and quality assessment of items. Not all items have reviews — community items tend to have more user feedback. Get user reviews for a specific Internet Archive item
get_views_stats
Returns total views and, when available, daily view counts and geographic breakdown. Use this to measure the popularity and reach of archived content. The identifier is the unique item ID from search results or the item URL. Get view count statistics for an Internet Archive item
search
The query parameter supports complex search syntax: AND, OR, NOT, wildcards (*), phrase matching ("..."), and field-specific searches (title:"X", subject:"Y"). Returns item identifiers, titles, media types, creators, dates, and collection info. Use this for broad searches across all media types. Optional fields parameter specifies which fields to return (comma-separated: "identifier,title,mediatype,creator,date,collection"). Default returns 25 rows; use rows to get up to 100 per page. Use page for pagination. Sort options: "date desc", "date asc", "title asc", "title desc", "creator asc", "downloads desc". Example queries: "moon landing", "subject:world war 2", "collection:prelinger". Search the Internet Archive for books, videos, audio, software, images, and more
search_by_collection
Common collections: "prelinger" (Prelinger Archives), "fedflix" (Federal government films), "gutenberg" (Project Gutenberg ebooks), "opensource_movies" (community films), "netlabels" (netlabel music), "softwarelibrary" (classic software), "tv" (TV news archive), "pubmed" (medical journal articles), "nasa" (NASA images and videos), "americanlibraries" (library collections). Returns items within that collection with their identifiers, titles, and metadata. Use this to browse or search within curated collections. Search for items in a specific Internet Archive collection
search_by_creator
The creator name should match how it appears in the item metadata (may be full name or organization name). Use this to find the complete works of an author, all films by a director, or all content from an organization. Example creators: "George Orwell", "Charlie Chaplin", "NASA", "Project Gutenberg". Search for items created by a specific person or organization
search_by_date_range
Combines a search query with year filtering to find historical content from a specific era. Use this to find content from specific decades or periods. Example: query="science fiction", startYear="1950", endYear="1959" finds 1950s sci-fi. The query parameter can be any valid search term. Years should be 4-digit format. Search for items within a specific year range
search_by_mediatype
Media types include: "texts" (books, articles, documents), "movies" (films, videos, TV clips), "audio" (music, podcasts, radio, audiobooks), "software" (classic PC games, applications), "image" (photos, artwork, maps), "dataset" (data files), "web" (web pages). Use this when you want to find only items of a specific format. Example: mediatype="movies" returns only video content. Search for items of a specific media type in the Internet Archive
wayback_availability
Returns the closest (most recent) archived snapshot with its timestamp and availability status. Use this to find archived versions of websites, verify if a page is preserved, or get the date of the most recent snapshot. The archived URL can be accessed at: https://web.archive.org/web/{timestamp}/{original_url}. Example: For https://example.com, returns the closest archived snapshot date and URL. Check if a URL has been archived by the Wayback Machine and find available snapshots
Example Prompts for Internet Archive in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Internet Archive immediately.
"Search for public domain films from the 1940s."
"Check if https://example.com has been archived."
"Show me all NASA images available."
Troubleshooting Internet Archive MCP Server with Pydantic AI
Common issues when connecting Internet Archive to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiInternet Archive + Pydantic AI FAQ
Common questions about integrating Internet Archive MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect Internet Archive with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Internet Archive to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.