Provides web search capabilities using DuckDuckGo as a search provider, returning links, titles, and snippets from search results.
Provides web search capabilities using Google as a search provider, returning links, titles, and snippets from search results.
MCP MyZ Search
Poorman's search mcp.
Usage
Command line options
Server Parameters (startup only)
--port <number>orMYZ_SEARCH_PORT(fallbackPORT), default3000.--proxy <http|socks URL>orMYZ_SEARCH_PROXYapplied to Playwright.--timeout <ms>orMYZ_SEARCH_TIMEOUTfor navigation/default timeouts.--profile <dir>orMYZ_SEARCH_PROFILE_DIRto persist session/cookies.--human-wait <ms>orMYZ_SEARCH_HUMAN_WAITto allow human challenge solve in non-headless.
MCP HTTP Endpoint
Streamable HTTP MCP at
POST /mcpusing@modelcontextprotocol/sdk.Tools:
search-linksargs{ q: string; limit?: number<=50; provider?: 'bing'|'duckduckgo'|'google' }returns{ results: Array<{link,title,snippet}>, total }.Provider defaults to
bing, or you can change it via--default-providerswitch.
extract-page-textargs{ url: string; selector?: string }returns{ text, isContentPage, url, message }.
Providers
bingduckduckgogoogle
Examples
Custom port + proxy:
npx mcp-myz-search --port 3100 --proxy socks5://127.0.0.1:1080Persistent profile + human wait:
npx mcp-myz-search --headed --profile ~/.myz-bing --human-wait 20000
Notes
The server reuses a single Playwright browser/context/page and serializes access to improve performance.
Challenge pages are detected; when not using API, you can allow human solve via
--human-waitin non-headless mode.Text extraction prefers
main,#content,article, or a provided selector; returns a message when content is not found.