Captcha-avoiding web, news, image and video search plus page fetching over free sources
Maintain this server? Claim it
This server only runs locally, from a package. Install it with the instructions on this page to try it.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add multi-websearch-mcp \ -e WEBSEARCH_UA=YOUR_WEBSEARCH_UA \ -- uvx multi-websearch-mcp==0.3.0rc2
Environment
WEBSEARCH_UA (required): User-Agent with your contact (e-mail or URL), e.g. 'websearch/0.3 ([email protected])'; Wikimedia, GDELT and Hacker News ask for itSEARXNG_URL (optional, not in the config above): Your SearXNG instance (default http://127.0.0.1:8888); without it the feeds and APIs still answerWEBSEARCH_MCP_PAID (optional, not in the config above): 0 = agents may never use paid APIsWe don't run packages, so we can't list this server's tools.