What is wayback-machine-mcp CLAUDE.md?

Project instructions for a Python server that connects coding agents to the Internet Archive’s Wayback Machine, a service that stores older versions of web pages. It covers searching sites, finding saved snapshots, checking availability, and reading archived content and metadata.

Use it when developing, testing, or maintaining tools that search archived websites, inspect snapshots, retrieve page content, or read archive metadata.

It gives developers the project structure, API response shapes, configuration rules, and testing guidance needed to change the server safely.

How lakshyamehta03/wayback-machine-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lakshyamehta03/wayback-machine-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lakshyamehta03/wayback-machine-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lakshyamehta03/wayback-machine-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lakshyamehta03/wayback-machine-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/lakshyamehta03/wayback-machine-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lakshyamehta03/wayback-machine-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lakshyamehta03/wayback-machine-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lakshyamehta03/wayback-machine-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lakshyamehta03/wayback-machine-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 639 This file is loaded in full into every session.

When invoked 639 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00639	$0.00639
Opus 5	$0.00319	$0.00319
Sonnet 5	$0.00128	$0.00128
Haiku 4.5	$0.00064	$0.00064

Measured 11d ago against content hash ca04bf006cbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wayback-machine-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wayback-mcp

Python MCP server giving Claude structured access to the Internet Archive's Wayback Machine.

Documentation

research/PRD.md — Full product requirements, implementation decisions, and testing plan; primary reference for implementation
research/design-decisions.md — Finalized decisions from design review; supersedes open questions in the research doc
research/wayback-mcp-research.md — API feasibility study, prior art, original architecture and MCP surface area design
agent-response.txt — Verified live API response shapes for all 6 endpoints, including edge cases; authoritative reference for parsers and test mocks

Project structure

src/                           # Python source — maps to wayback_mcp package
  server.py          # MCP entry point, tool/prompt/resource registration
  config.py          # Rate limits, timeouts, endpoint URLs, User-Agent, result caps
  models.py          # All Pydantic input/output models (centralized)
  tools/
    search.py        # search_archive, search_domain
    snapshots.py     # lookup_snapshots, check_availability
    content.py       # get_snapshot_content, get_item_metadata
  client/
    http.py          # httpx.AsyncClient, User-Agent injection, retry logic
    rate_limiter.py  # Async token-bucket per named endpoint key, 429 back-off
    parsers.py       # Raw API responses → typed Pydantic models
tests/
  test_search.py
  test_snapshots.py
  test_content.py
  test_client.py
  integration/       # Real IA API calls — run with pytest --integration

Commands

uv run mcp-server-wayback      # run server (stdio)
uv run pytest                  # unit tests (mocked via respx)
uv run pytest --integration    # unit + integration tests (hits live IA APIs)

Constraints

All outbound requests must pass through client/rate_limiter.py — never call IA APIs directly from tool files
All tuneable values (rate limits, result caps, endpoint URLs, User-Agent) live in config.py
Tool handlers are async def throughout; use httpx.AsyncClient
Expected failures (snapshot not found, unsupported MIME type, rate limited) return structured errors via ToolError; unexpected failures raise exceptions
Pydantic models are defined in src/models.py (installed as wayback_mcp.models), not inline in tool files

Read the full file on GitHub · 64 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 64 lines · 639 tokens per session scan A ca04bf006cbf

Subscribe to this mod's changes

wayback-machine-mcp CLAUDE.md is an instructions file published in the GitHub repository lakshyamehta03/wayback-machine-mcp (3 stars, last pushed 3mo ago), licensed MIT. It adds 639 tokens to every session, about $0.0032 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation LLM Research ai anthropic archive claude internet-archive

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

wayback-machine-mcp: Instructions file for Claude Code