open-search-mcp
Related Servers
Alternatives to open-search-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables MCP clients to search the web and fetch individual pages through two stdio tools, returning ranked results or extracted page content, titles and outbound links. It wraps a hosted, API-key-authenticated service (or a local daemon) with zero runtime dependencies.19 npmMIT
- AlicenseAqualityCmaintenanceGives MCP-capable agents live web access: search the web, scrape pages into Markdown (including JavaScript-heavy and bot-protected sites), and extract named fields as JSON, with job polling, token-aware content offloading, and built-in research guidance. Ships as a self-hostable stdio or HTTP service with spend caps and per-request key support.7MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that provides web search scraping from DuckDuckGo (with Mojeek fallback) and URL content fetching as markdown/text or raw HTML.1ISC
- AlicenseAqualityAmaintenanceEnables AI agents to run web and image searches across nine engines with automatic fallback and ad filtering, fetch pages and PDFs as Markdown, and search WeChat Official Account articles — all without requiring a search account or API key out of the box. Works over stdio or Streamable HTTP with any MCP-capable client.5479 npmApache 2.0
- AlicenseNot gradedqualityAmaintenanceGives any MCP client keyless web, news, semantic, and GitHub search plus a token-efficient reader-mode page and text-PDF fetcher, with engine fallback and a local sqlite cache. It enables agents to keep researching the web without API keys, signups, or account quotas.MIT
- AlicenseAqualityAmaintenanceEnables MCP clients to search the live web and fetch any URL as clean text through Ollama's web search and fetch APIs, returning ranked results with page text and outgoing links. Runs as a single dependency-free stdio server, so agents can ground their answers with current web content without a separate search vendor.219 npmMIT
TDQS
Scored across 3 tools
fetch, search, and research target distinct inputs (URL vs query vs combined workflow), but research is a composite of search+fetch and could be over-selected when simpler tools suffice. Descriptions clarify the boundaries well, so misselection risk is minor.
All three tool names are single lowercase verbs (fetch, search, research), forming a consistent action-oriented pattern with no deviations. This makes the set predictable and easy to scan.
Three tools is lean but perfectly scoped for a web search and content extraction server. Each tool earns its place: one for URL fetching, one for search queries, and one for combined research.
Core operations (search, fetch, combined research) are well covered, with no dead ends for typical workflows. Minor gaps include no batch fetch for a list of known URLs and no pagination beyond max_results for deeper search.