clawhub install olostep

{
  "mcpServers": {
    "olostep": {
      "command": "npx",
      "args": ["-y", "olostep-mcp"],
      "env": {
        "OLOSTEP_API_KEY": "your-api-key-here"
      }
    }
  }
}

map → discover all URLs on the docs site
batch → scrape every page in parallel as clean markdown
→ feed into your vector store

map → find all product/listing URLs
batch → scrape with a pre-built parser for typed JSON
→ pipe into your database, API, or seed files

npm install olostep

import Olostep from 'olostep';

const client = new Olostep({ apiKey: process.env.OLOSTEP_API_KEY });

// Scrape a page to markdown
const scrape = await client.scrapes.create('https://example.com');
console.log(scrape.markdown_content);

// Batch scrape with custom IDs
const batch = await client.batches.create([
  { url: 'https://example.com/page-1', customId: 'p1' },
  { url: 'https://example.com/page-2', customId: 'p2' },
]);

// Crawl a site
const crawl = await client.crawls.create({
  url: 'https://docs.example.com',
  maxPages: 50,
  maxDepth: 3,
});

// Discover URLs
const map = await client.maps.create({
  url: 'https://example.com',
  topN: 100,
  searchQuery: 'pricing',
});

pip install olostep

from olostep import Olostep

client = Olostep()  # reads OLOSTEP_API_KEY from env

# Scrape
result = client.scrapes.create(url_to_scrape="https://example.com")
print(result.markdown_content)

# Batch
batch = client.batches.create(urls=["https://example.com", "https://example.org"])

# Crawl
crawl = client.crawls.create(start_url="https://docs.example.com", max_pages=50)

# Map
site_map = client.maps.create(url="https://example.com")

# AI Answers with structured output
answer = client.answers.create(
    task="Compare Stripe vs Square pricing",
    json_format={"providers": [{"name": "", "pricing": "", "best_for": ""}]},
)

pip install pytest
pytest tests/test_skill_integrity.py -v

OLOSTEP_API_KEY=your_key pytest tests/test_live_api.py -v --timeout=60

olostep-clawhub-plugin/
  .clawhub/
    plugin.json          # Plugin metadata, keywords, logo reference
  .github/
    workflows/
      integrity.yml      # CI: static checks on PR, live tests on push to main
  skills/
    answers/SKILL.md     # AI-powered answers with citations
    batch/SKILL.md       # Batch scrape up to 10k URLs
    crawl/SKILL.md       # Autonomous website crawling
    debug-error/SKILL.md # Error debugging from live web
    docs-to-code/SKILL.md # Write code from scraped docs
    extract-schema/SKILL.md # Structured data extraction
    integrate/SKILL.md   # Auto-detect stack, write SDK integration
    map/SKILL.md         # URL discovery and site mapping
    migrate-code/SKILL.md # Framework migration from docs
    research/SKILL.md    # Multi-source competitive research
    scrape/SKILL.md      # Single-page scraping
    search/SKILL.md      # Web search (3 modes)
    setup/SKILL.md       # API key configuration
  tests/
    conftest.py          # Shared fixtures, known MCP tools, stale params
    test_skill_integrity.py  # Static validation of all SKILL.md files
    test_live_api.py     # Live API smoke tests
  mcp.json               # MCP server configuration
  LICENSE                 # MIT
  README.md