A side-by-side look at the Open WebSearch and MinerU Open MCP 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 MinerU Open MCP for search & data extraction as a local process. You can also run both side by side in one mcpServers block.
search, fetchLinuxDoArticle, fetchCsdnArticle.parse_documents, get_ocr_languages.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 71/100 · Great | 61/100 · 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 | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1,867 | 222 |
| Directory activity | 3 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 6 | 2 |
| Full listing | View Open WebSearch | View MinerU Open MCP |
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 URLparse_documentsConvert PDF, Office (DOCX, PPTX), spreadsheets (XLSX in Flash mode), images, and http(s) URLs to Markdown using the MinerU cloud API (content is uploaded to mineru.net; do not use for data that must stay on-device). Does not modify source files; may write Markdown under output_dir when saving results.
Auth: without MINERU_API_TOKEN, Flash mode applies (Markdown-only, about 20 pages and 10 MB per file; service rate limits). With MINERU_API_TOKEN, higher limits and optional formats per plan.
Use for extraction and conversion. Use get_ocr_languages only to list OCR language codes, not to parse files. Not for fully offline parsing.
Parameters: file_sources is paths/URLs or objects with source and pages for PDF ranges; language is an OCR code (default ch); enable_ocr defaults to auto (null); set model to html only if every source is a web page URL.get_ocr_languagesReturn supported MinerU OCR and script language codes (e.g. ch, en, japan, latin). Read-only; no uploads. Use before setting the language argument on parse_documents for scanned or multilingual documents. Do not use for file conversion; call parse_documents instead.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": {
"mineru-open-mcp": {
"command": "uvx",
"args": [
"mineru-open-mcp"
]
}
}
}