Free web search for AI agents. No API key required. Hosted MCP in active development.
Connect Remote server
claude mcp add --transport http search https://api.ssearch.cc/mcp
{
"mcpServers": {
"search": {
"url": "https://api.ssearch.cc/mcp"
}
}
}
{
"servers": {
"search": {
"type": "http",
"url": "https://api.ssearch.cc/mcp"
}
}
}
Settings > Connectors > Add custom connector
URL: https://api.ssearch.cc/mcp
Tools 8 found in our last check
search_webSearch SSearch. Set wait_for_coverage to search owned documents and, only if needed, external discovery on a miss.
search_documentsSearch SSearch-owned stored full-text documents. Successful misses can be promoted into the live index.
get_contextRetrieve only the stored passages in a search result that are relevant to the information you need.
get_documentRetrieve the broader stored text for a known SSearch document ID.
fetch_pageFetch and extract readable page text; optionally fall back to Common Crawl.
search_planShow the normalized local search plan for a query.
search_sourcesDescribe the local SSearch corpus and search backends.
forward_canaryDev-only transport proof. Forward a fake canary transiently and return only delivery status. Never use a real credential.
Details
| Endpoint | https://api.ssearch.cc/mcp (Streamable HTTP) |
| First published | 23 Sep 2026 |
| Last updated | 23 Sep 2026 |
| Registry name | cc.ssearch/search |
More search and web servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
