Web Search (Tanod) is answering right now. Last checked 7 min ago. It exposes 3 tools.
Search the web and the news from an agent, with page text in the results when you ask for it.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.
claude mcp add web-search --transport http https://tanod.dev/mcp/web-search
https://tanod.dev/mcp/web-search
[mcp_servers.web-search]
url = "https://tanod.dev/mcp/web-search"
{
"mcpServers": {
"web-search": {
"url": "https://tanod.dev/mcp/web-search"
}
}
}
{
"servers": {
"web-search": {
"type": "http",
"url": "https://tanod.dev/mcp/web-search"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
news_search
web_search
search_with_contents
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://tanod.dev/mcp/web-search | streamable-http | answering | 326 ms | 7 min ago |
Search the web and fetch pages with sourced results, optimized for AI agents
Search the web, news, images, videos and books, and extract page content for AI agents.
Web search and clean-text page fetch for AI agents, with SSRF protection.
Search with Brave Search API: web results, news results.
Web search and page fetch for AI agents. Results come from a shared cache; cached calls cost less.
Web search for agents: page to Markdown, screenshots, news search, metadata, sitemaps and RDAP.
Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.
Web search with full-page content and grounded answers from the Staan API.
Answers built from our own checks of this server.