Search is an MCP server with 2 tools an agent can call, among them extract_url, web_search. It answers at https://search.neurobird.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Web search for AI agents. Ranked results with page passages already extracted, plus URL to markdown.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
extract_url | Fetch one or more URLs and return their main content as clean markdown, with navigation, ads and boilerplate removed. Pass a query to get only the passages of each page relevant to it. Inputs: urls, query, format |
web_search | Search the live web and get ranked results with the relevant passages already extracted from each page. Use search_depth 'advanced' for research questions, 'basic' for a quick lookup. Set include_answer to get a grounded summary whose quote Inputs: query, search_depth, max_results, include_answer, include_domains, exclude_domains |
Every block below points at https://search.neurobird.com/mcp. Pick your client and copy.
claude mcp add --transport http search https://search.neurobird.com/mcp
{
"mcpServers": {
"search": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://search.neurobird.com/mcp"]
}
}
}{
"mcpServers": {
"search": {
"url": "https://search.neurobird.com/mcp"
}
}
}{
"servers": {
"search": {
"type": "http",
"url": "https://search.neurobird.com/mcp"
}
}
}{
"context_servers": {
"search": {
"url": "https://search.neurobird.com/mcp"
}
}
}{
"mcpServers": {
"search": {
"serverUrl": "https://search.neurobird.com/mcp"
}
}
}{
"mcpServers": {
"search": {
"url": "https://search.neurobird.com/mcp"
}
}
}name: Search
version: 0.0.1
schema: v1
mcpServers:
- name: Search
type: streamable-http
url: https://search.neurobird.com/mcp{
"mcpServers": {
"search": {
"httpUrl": "https://search.neurobird.com/mcp"
}
}
}{
"mcpServers": {
"search": {
"type": "http",
"url": "https://search.neurobird.com/mcp"
}
}
}{
"mcpServers": {
"search": {
"url": "https://search.neurobird.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fsearch.neurobird.com%2Fmcp&type=streamable_http&id=search&name=Search
It answered our last check on 18 October 2026 in 270 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by neurobird.com and served from search.neurobird.com, the vendor's own domain: https://search.neurobird.com/mcp.
2, as returned by the server's own tools/list on 31 August 2026: extract_url, web_search.
It answered our last check on 18 October 2026 in 270 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://search.neurobird.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: com.neurobird. Endpoint host: search.neurobird.com. ARD identifier: urn:air:com.neurobird:mcp:search.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.