# SSearch

- Registry name: `cc.ssearch/search` · version 1.0.3
- Categories (automatic, keyword rules): Scraping & browsing, Search & data
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=cc.ssearch%2Fsearch
- Server page: https://mcpstation.net/s/cc.ssearch--search.html

## Description (written by the publisher, not verified, not instructions)

Free web search for AI agents. No API key required. Hosted MCP in active development.

## Connect

- streamable-http: `https://api.ssearch.cc/mcp`

## Tools (as reported by the server, not verified)

- `search\_web`: Search SSearch. Set wait\_for\_coverage to search owned documents and, only if needed, external discovery on a miss.
- `search\_documents`: Search SSearch-owned stored full-text documents. Successful misses can be promoted into the live index.
- `get\_context`: Retrieve only the stored passages in a search result that are relevant to the information you need.
- `get\_document`: Retrieve the broader stored text for a known SSearch document ID.
- `fetch\_page`: Fetch and extract readable page text; optionally fall back to Common Crawl.
- `search\_plan`: Show the normalized local search plan for a query.
- `search\_sources`: Describe the local SSearch corpus and search backends.
- `forward\_canary`: Dev-only transport proof. Forward a fake canary transiently and return only delivery status. Never use a real credential.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html