olostep
Olostep v1.0.0
Turn any website into clean, LLM-ready markdown or structured data. Olostep integrates powerful web scraping, crawling, search, and AI-powered answers directly into Claude Code. Scrape single pages...
From the developer
License
MIT
Declared components
Skills · Mcp servers
Works with
Claude Code
Description
From the marketplace listing
Turn any website into clean, LLM-ready markdown or structured data. Olostep integrates powerful web scraping, crawling, search, and AI-powered answers directly into Claude Code. Scrape single pages, crawl entire sites, map site structures, batch-process thousands of URLs, and search the web — all with automatic JavaScript rendering, anti-bot bypasses, and real-time extraction built in. The plugin includes an AI answers tool that goes beyond scraping: describe what you need in plain language and Olostep searches the live web, synthesizes the results, and returns a source-backed answer with structured JSON output — no URLs required. How to use: After installing, set your OLOSTEP_API_KEY environment variable. Then use these commands to get started: /olostep:scrape — Extract any webpage as clean markdown, HTML, or structured JSON. /olostep:crawl — Crawl and extract content from an entire website. /olostep:search — Search the web and get deduplicated results with titles and descriptions. /olostep:map — Discover all URLs on a site instantly. /olostep:answer — Ask a question in plain language and get a source-backed answer from live web data. /olostep:batch — Scrape up to 10,000 URLs in a single async job. You can also use Olostep's tools directly in conversation: ask Claude to scrape a URL, search for recent information, extract structured data with a custom schema, or research competitors across multiple sites.
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Web scraping and crawling powered by Firecrawl. Turn any website into clean, LLM-ready markdown or structured data. Scrape single pages, ...
Shared terms: scrape, single, web, search
-
Anakin turns any website into clean, LLM-ready data directly from Claude Code. Scrape single pages or batch up to 10 URLs at once, return...
Shared terms: clean, llm, markdown, scrape
-
Universal web content extraction — convert any URL to clean, LLM-ready markdown. Supports HTML pages (with content density filtering and ...
Shared terms: clean, llm, markdown, web
-
The complete web toolkit for your agent. Search the web and get answers in milliseconds. Fetch any URL and get clean markdown content bac...
Shared terms: answer, clean, markdown, web
-
A Claude Code plugin that integrates Querit.ai's powerful search API, enabling Claude to access real-time web information, technical docu...
Shared terms: integrate, powerful, web, search
Keywords
Files & skills
olostep · catalog manifest
Saved declaration
{}
olostep · catalog manifest
Saved declaration
{
"name": "olostep",
"source": {
"sha": "b32ad4d5f459821e331fe00fe942aa28a4ee5ea3",
"url": "https://github.com/olostep/olostep-claude-code-plugin.git",
"source": "url"
},
"homepage": "https://www.olostep.com/",
"description": "Turn any website into clean, LLM-ready markdown or structured data. Olostep integrates powerful web scraping, crawling, search, and AI-powered answers directly into Claude Code. Scrape single pages, crawl entire sites, map site structures, batch-process thousands of URLs, and search the web — all with automatic JavaScript rendering, anti-bot bypasses, and real-time extraction built in.\nThe plugin includes an AI answers tool that goes beyond scraping: describe what you need in plain language and Olostep searches the live web, synthesizes the results, and returns a source-backed answer with structured JSON output — no URLs required.\nHow to use: After installing, set your OLOSTEP_API_KEY environment variable. Then use these commands to get started:\n/olostep:scrape — Extract any webpage as clean markdown, HTML, or structured JSON.\n/olostep:crawl — Crawl and extract content from an entire website.\n/olostep:search — Search the web and get deduplicated results with titles and descriptions.\n/olostep:map — Discover all URLs on a site instantly.\n/olostep:answer — Ask a question in plain language and get a source-backed answer from live web data.\n/olostep:batch — Scrape up to 10,000 URLs in a single async job.\nYou can also use Olostep's tools directly in conversation: ask Claude to scrape a URL, search for recent information, extract structured data with a custom schema, or research competitors across multiple sites."
}
olostep · catalog manifest
Skills
"./skills/"
Mcp servers
"./.mcp.json"
Saved declaration
{
"name": "olostep",
"author": {
"name": "Olostep",
"email": "support@olostep.com"
},
"skills": "./skills/",
"license": "MIT",
"version": "1.0.0",
"homepage": "https://olostep.com",
"keywords": [
"web-scraping",
"web-search",
"crawling",
"markdown-extraction",
"ai-answers",
"batch-scraping",
"content-extraction",
"mcp"
],
"mcpServers": "./.mcp.json",
"repository": "https://github.com/olostep/olostep-claude-code-plugin",
"description": "Turn any website into clean, LLM-ready markdown or structured data. Olostep integrates powerful web scraping, crawling, search, and AI-powered answers directly into Claude Code. Scrape single pages, crawl entire sites, map site structures, batch process up to 10k URLs, and search the web — all with automatic JavaScript rendering, anti-bot handling, and proxy rotation built in."
}
plugin.json observed Nov 6, 2026 · 10:47 UTC. Manifest source ↗
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install olostep@claude-community
Technical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 7, 2026 · 00:08 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.