Search is answering right now. Last checked 2 min ago. It exposes 2 tools. Last commit 31 Aug 2026.
Web search for AI agents. Ranked results with page passages already extracted, plus URL to markdown.
Today is the operative word: we check Search every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add search --transport http https://search.neurobird.com/mcp
{
"mcpServers": {
"search": {
"url": "https://search.neurobird.com/mcp"
}
}
}
[mcp_servers.search]
url = "https://search.neurobird.com/mcp"
{
"mcpServers": {
"search": {
"url": "https://search.neurobird.com/mcp"
}
}
}
{
"mcpServers": {
"search": {
"url": "https://search.neurobird.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
extract_url
web_search
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://search.neurobird.com/mcp | streamable-http | answering | 167 ms | 2 min ago |
Search the web and fetch pages with sourced results, optimized for AI agents
Web search, fetch, extract, and research for AI agents. Markdown output + AI-synthesized answers.
Real-time web search and page fetch for AI agents from Andi's own index. LLM-ready markdown output.
Web search, page reading and structured extraction for AI agents, with strong RU coverage
AI-powered web research MCP server for agents. Supports web search, browse page, extract...
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Web search and URL-to-markdown for agents. Pay per call in USDC on Base, no signup.
Web search and page extraction for agents, returned as readable text rather than raw JSON.
Answers built from our own checks of this server.