A side-by-side look at the Atlas Web Compiler & Scraper and Metalift MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Atlas Web Compiler & Scraper for search & data extraction work as a local process; choose Metalift for search & data extraction as a local process. You can also run both side by side in one mcpServers block.
ATLAS_API_KEY.atlas_scrape, atlas_compile, atlas_map.METALIFT_API_KEY, METALIFT_API_URL.metalift_scrape, metalift_batch_scrape, metalift_crawl.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 60/100 · Good | 48/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | ATLAS_API_KEY | METALIFT_API_KEYMETALIFT_API_URL |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 0 |
| Directory activity | 1 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 5 | 11 |
| Full listing | View Atlas Web Compiler & Scraper | View Metalift |
atlas_scrapeQuickly extract clean, readable text, markdown, and links from a web page using Atlas's fast synchronous parser. Strips cookie banners, navigation clutter, and ads. Best for articles, documentation pages, and general web reading.atlas_compileCompile a public web page into clean, deterministic, LLM-optimized markdown or structured AST nodes using the full 12-pass Atlas compiler. Strips boilerplate and generates section hierarchies. Best for complex documentation, API references, and dense technical articles.atlas_mapDiscover the URL topology, sitemap structure, and hierarchy of a website without compiling individual pages. Use before crawling to identify relevant documentation paths and section boundaries.atlas_batch_compileCompile a bounded list of explicit URLs in parallel. Returns clean markdown for each page within a consolidated budget. Maximum 20 URLs per batch call.atlas_crawlTraverse and compile a bounded subsection of a website (such as an API reference or documentation folder) starting from a seed URL. Returns consolidated page summaries and navigable resource URIs.metalift_scrapeScrape a single URL (default: fast direct static markdown, **`response_detail=compact`**; use `standard` / `full` for more)metalift_batch_scrapeScrape multiple URLs (same `response_detail`; default `compact`)metalift_crawlCrawl a websitemetalift_mapDiscover site URLs from page HTML linksmetalift_sitemapFetch XML sitemap URLs (robots.txt / sitemap.xml)metalift_web_searchWeb search — top 10 SERP results (title, url, snippet). **2 credits** per search. Does not fetch page content; use `metalift_scrape` separately for URLs you needmetalift_job_statusPoll async jobsmetalift_list_strategiesList scrape strategiesmetalift_seed_sessionStore browser session cookies for a domainmetalift_warm_sessionWarm WAF/retail cookiesmetalift_list_sessionsList stored domain sessionsPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"atlas-web-compiler-scraper": {
"command": "npx",
"args": [
"-y",
"@atlascompiler/mcp"
],
"env": {
"ATLAS_API_KEY": "YOUR_ATLAS_API_KEY_HERE"
}
}
}
}
{
"mcpServers": {
"metalift": {
"command": "npx",
"args": [
"-y",
"@metalift/mcp"
],
"env": {
"METALIFT_API_KEY": "YOUR_METALIFT_API_KEY_HERE",
"METALIFT_API_URL": "YOUR_METALIFT_API_URL_HERE"
}
}
}
}