M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionSearXNG SearchPrivate web search through SearXNG.Firecrawl MCP ServerFirecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
FMRS61 / 100 · C75 / 100 · B
Reliability10 / 2013 / 20
Security and permissions12 / 2012 / 20
Maintenance10 / 2016 / 20
Documentation16 / 2017 / 20
Setup experience13 / 2017 / 20
Best for
  • Users who want self-hosted search infrastructure
  • Teams with an existing SearXNG instance and privacy requirements
  • MCP clients that need paginated search and URL reading
  • Scenarios needing clean, structured web context fed to an AI assistant
  • Users already on the Firecrawl platform who want to call its scraping capability directly via MCP
Not for
  • Users without an accessible SearXNG instance
  • Users seeking a native SearXNG plugin installation
  • Workflows that require reading PDFs, media, archives, or other binary downloads
  • Simple static-page scraping where you don't want to depend on a third-party API and incur call costs
  • Sites that explicitly disallow automated access (robots.txt)
Required permissions
  • Requires access to the configured SEARXNG_URL, which the manifest marks as required and secret.
  • May use AUTH_USERNAME and AUTH_PASSWORD for legacy global SearXNG Basic Auth.
  • Search queries are passed to external search services, and web_url_read makes requests to user-specified URLs.
  • Requires a Firecrawl API key to call; cost and quota are governed by the Firecrawl account
  • firecrawl_agent/firecrawl_interact perform automated browser interaction, which may trigger login or form-submission flows on the target site
Risks and side effects
  • Privacy depends on the connected SearXNG instance and its configuration.
  • Search queries may be passed to external services used by SearXNG.
  • URL reading creates outbound requests; private or internal URLs and redirects are blocked by default, but network deployments should still enable and configure hardening.
  • HTML fallback depends on the instance's page structure and may return fewer results without relevance scores or engine names.
  • Bulk crawl/map tools can generate significant request volume against a target site — respect the site's rate limits and terms of service
  • firecrawl_agent's interactive action chain is longer — define task boundaries clearly before running it to avoid accidentally triggering actions on a sensitive site
Supported clientsClaude Desktop, CursorClaude Desktop, VS Code, Cursor, Windsurf, Zed, Amp
Tools411