Connect SSearch and your agent gets 7 tools, among them fetch_page, get_context, get_document. It answers at https://api.ssearch.cc/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 4 of 4 times since 17 September 2026; the last check, on 24 October 2026, succeeded.
Free web search for AI agents. No API key required. Hosted MCP in active development.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
fetch_page | Fetch and extract readable page text; optionally fall back to Common Crawl. Inputs: url, archive_fallback, max_chars |
get_context | Retrieve only the stored passages in a search result that are relevant to the information you need. Inputs: document_id, query, max_chars, max_passages |
get_document | Retrieve the broader stored text for a known SSearch document ID. Inputs: document_id, max_chars |
search_documents | Search SSearch-owned stored full-text documents. Successful misses can be promoted into the live index. Inputs: query, max_results, promote |
search_plan | Show the normalized local search plan for a query. Inputs: query |
search_sources | Describe the local SSearch corpus and search backends. |
search_web | Search SSearch. Set wait_for_coverage to search owned documents and, only if needed, external discovery on a miss. Inputs: query, max_results, fresh, wait_for_coverage |
Every block below points at https://api.ssearch.cc/mcp. Pick your client and copy.
claude mcp add --transport http ssearch https://api.ssearch.cc/mcp
{
"mcpServers": {
"ssearch": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.ssearch.cc/mcp"]
}
}
}{
"mcpServers": {
"ssearch": {
"url": "https://api.ssearch.cc/mcp"
}
}
}{
"servers": {
"ssearch": {
"type": "http",
"url": "https://api.ssearch.cc/mcp"
}
}
}{
"context_servers": {
"ssearch": {
"url": "https://api.ssearch.cc/mcp"
}
}
}{
"mcpServers": {
"ssearch": {
"serverUrl": "https://api.ssearch.cc/mcp"
}
}
}{
"mcpServers": {
"ssearch": {
"url": "https://api.ssearch.cc/mcp"
}
}
}name: SSearch
version: 0.0.1
schema: v1
mcpServers:
- name: SSearch
type: streamable-http
url: https://api.ssearch.cc/mcp{
"mcpServers": {
"ssearch": {
"httpUrl": "https://api.ssearch.cc/mcp"
}
}
}{
"mcpServers": {
"ssearch": {
"type": "http",
"url": "https://api.ssearch.cc/mcp"
}
}
}{
"mcpServers": {
"ssearch": {
"url": "https://api.ssearch.cc/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.ssearch.cc%2Fmcp&type=streamable_http&id=ssearch&name=SSearch
It answered our last check on 24 October 2026 in 458 ms. Over 4 checks since 17 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by ssearch.cc and served from api.ssearch.cc, the vendor's own domain: https://api.ssearch.cc/mcp.
7, as returned by the server's own tools/list on 24 September 2026: fetch_page, get_context, get_document, search_documents, search_plan, search_sources, search_web.
It answered our last check on 24 October 2026 in 458 ms. Over 4 checks since 17 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.ssearch.cc/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: cc.ssearch. Endpoint host: api.ssearch.cc. ARD identifier: urn:air:cc.ssearch:mcp:search.
First indexed 17 September 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.