Brainiall Web is an MCP server with 5 tools an agent can call, among them check_web_service, crawl_site, map_site. It answers at https://api.brainiall.com/mcp/web/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 7 of 10 times since 4 September 2026; the last check, on 18 October 2026, succeeded.
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
check_web_service | Check whether the web reading service is responding. |
crawl_site | Read multiple linked pages with strict page and depth limits. Use only when several pages are required. If you merely need to discover a site's structure, use map_site first because crawling is slower and costlier. Inputs: url, max_pages, max_depth |
map_site | List a site's URLs so an agent can select pages before reading them. Prefer this inexpensive discovery step before crawl_site. Map first, then call read_page for selected URLs unless content from many pages is required. Inputs: url, limit |
read_page | Read one known web page as clean Markdown without raw HTML noise. Use this for documentation, articles, and product pages when the URL is already known. For an unfamiliar site, use map_site first to choose useful URLs instead of crawling ev Inputs: url |
search_web | Find relevant web pages when you do not already know their URLs. Inputs: query, max_results |
Every block below points at https://api.brainiall.com/mcp/web/mcp. Pick your client and copy.
claude mcp add --transport http brainiall-web https://api.brainiall.com/mcp/web/mcp
{
"mcpServers": {
"brainiall-web": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.brainiall.com/mcp/web/mcp"]
}
}
}{
"mcpServers": {
"brainiall-web": {
"url": "https://api.brainiall.com/mcp/web/mcp"
}
}
}{
"servers": {
"brainiall-web": {
"type": "http",
"url": "https://api.brainiall.com/mcp/web/mcp"
}
}
}{
"context_servers": {
"brainiall-web": {
"url": "https://api.brainiall.com/mcp/web/mcp"
}
}
}{
"mcpServers": {
"brainiall-web": {
"serverUrl": "https://api.brainiall.com/mcp/web/mcp"
}
}
}{
"mcpServers": {
"brainiall-web": {
"url": "https://api.brainiall.com/mcp/web/mcp"
}
}
}name: Brainiall Web
version: 0.0.1
schema: v1
mcpServers:
- name: Brainiall Web
type: streamable-http
url: https://api.brainiall.com/mcp/web/mcp{
"mcpServers": {
"brainiall-web": {
"httpUrl": "https://api.brainiall.com/mcp/web/mcp"
}
}
}{
"mcpServers": {
"brainiall-web": {
"type": "http",
"url": "https://api.brainiall.com/mcp/web/mcp"
}
}
}{
"mcpServers": {
"brainiall-web": {
"url": "https://api.brainiall.com/mcp/web/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.brainiall.com%2Fmcp%2Fweb%2Fmcp&type=streamable_http&id=brainiall-web&name=Brainiall%20Web
It answered our last check on 18 October 2026 in 780 ms. Over 10 checks since 4 September 2026 it answered 7. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by brainiall.com and served from api.brainiall.com, the vendor's own domain: https://api.brainiall.com/mcp/web/mcp.
5, as returned by the server's own tools/list on 31 August 2026: check_web_service, crawl_site, map_site, read_page, search_web.
It answered our last check on 18 October 2026 in 780 ms. Over 10 checks since 4 September 2026 it answered 7.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.brainiall.com/mcp/web/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.brainiall. Endpoint host: api.brainiall.com. ARD identifier: urn:air:com.brainiall:mcp:web.
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.