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.
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
Enables web search across Bing, DuckDuckGo, and Google using Playwright automation, with tools for retrieving search results and extracting page text content.