A side-by-side look at the Open WebSearch and Atlas Web Compiler & Scraper MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Open WebSearch for search & data extraction work as a local process; choose Atlas Web Compiler & Scraper for search & data extraction as a local process. You can also run both side by side in one mcpServers block.
search, fetchLinuxDoArticle, fetchCsdnArticle.ATLAS_API_KEY.atlas_scrape, atlas_compile, atlas_map.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 72/100 · Great | 60/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | ATLAS_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1,871 | 1 |
| Directory activity | 6 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 6 | 5 |
| Full listing | View Open WebSearch | View Atlas Web Compiler & Scraper |
searchSearch the web using multiple engines (e.g., Baidu, Bing, DuckDuckGo, CSDN, Exa, Brave, Juejin(掘金), Startpage, Sogou(搜狗)) with no API key required. searchMode meanings: omit or set auto to use the server configured SEARCH_MODE; request forces request-based search; playwright forces browser-based search.fetchLinuxDoArticleFetch full article content from a linux.do post URLfetchCsdnArticleFetch full article content from a csdn post URLfetchGithubReadmeFetch README content from a GitHub repository URLfetchWebContentFetch content from a public HTTP(S) URL (supports Markdown files and normal web pages)fetchJuejinArticleFetch full article content from a Juejin(掘金) post URLatlas_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.Paste 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": {
"aas-ee-open-websearch": {
"command": "npx",
"args": [
"-y",
"open-websearch@latest"
]
}
}
}
{
"mcpServers": {
"atlas-web-compiler-scraper": {
"command": "npx",
"args": [
"-y",
"@atlascompiler/mcp"
],
"env": {
"ATLAS_API_KEY": "YOUR_ATLAS_API_KEY_HERE"
}
}
}
}