Python SDK for CRW web scraper — scrape, crawl, and map any website from Python
Most search and retrieval work still happens through a UI a human drives. Crw MCP server moves it into the conversation instead. Python SDK for CRW web scraper — scrape, crawl, and map any website from Python.
The web data API for AI agents — search, scrape, map, and crawl any site into clean markdown or JSON.
Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
The server publishes 13 tools. What each one is for:
Lighter — one static binary, ~50 MB RAM idle. No Redis, no Node, no Chromium heap in the request path — it runs on a $5 VPSDrop — in Firecrawl compatibility.** Migrate existing Firecrawl code by changing one base URLVerb — EndpointSearch — POST /v1/searchScrape — POST /v1/scrapeMap — POST /v1/mapCrawl — POST /v1/crawlExtract — POST /v1/extract (async, multi-URL) or POST /v1/scrape formats:["json"] (inline, one URL)Monitor — POST /v1/change-tracking/diffScale — Grows with you — 500 free credits to millions of pages/month, higher concurrency per tier, no capacity planningStart — Sign up — 500 free credits, no cardCost — Free tier, then plans from $11/mo — pricingConfiguration is passed through the environment: CRW_API_KEY, CRW_API_URL, YOUR_CRW_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the search and retrieval options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Crw's toolset — Lighter, Drop, Verb and 10 more — is a fair guide to whether it matches your workflow.
This entry was verified against Crw's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Lighter | one static binary, **~50 MB RAM idle**. No Redis, no Node, no Chromium heap in the request path — it runs on a $5 VPS. |
| Drop | in Firecrawl compatibility.** Migrate existing Firecrawl code by changing one base URL. |
| Verb | Endpoint |
| Search | POST /v1/search |
| Scrape | POST /v1/scrape |
| Map | POST /v1/map |
| Crawl | POST /v1/crawl |
| Extract | POST /v1/extract (async, multi-URL) or POST /v1/scrape formats:["json"] (inline, one URL) |
| Monitor | POST /v1/change-tracking/diff |
| Scale | Grows with you — 500 free credits to **millions of pages/month**, higher concurrency per tier, no capacity planning |
| Start | [Sign up](https://fastcrw.com/register) — **500 free credits, no card** |
| Cost | Free tier, then plans from **$11/mo** — [pricing](https://fastcrw.com/pricing) |
| Contributors | <sub>Everyone who has landed a commit, refreshed weekly from the contributor graph.</sub> |
{
"mcpServers": {
"crw": {
"command": "npx",
"args": ["-y", "crw-mcp"],
"env": {
"CRW_API_KEY": "your-value",
"CRW_API_URL": "your-value",
"YOUR_CRW_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| CRW_API_KEY | Credential the server authenticates with. | Yes |
| CRW_API_URL | Endpoint or connection string the server talks to. | Yes |
| YOUR_CRW_API_KEY | Credential the server authenticates with. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.