Search 12 .onion search engines. Results include BM25 confidence score. Results cached 30 min.
AI agents call sicry_search to retrieve information from Sicry without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
sicry_search retrieves query results from Tor search engines without creating, modifying, deleting, or executing code. It is a Read tool. Severity is elevated to medium (rather than low) because the tool enables queries over Tor hidden services, which could facilitate access to illicit content or information normally restricted; however, the tool itself performs only passive information retrieval.
From the tool's definition Tool description: 'Search 12 .onion search engines. Results include BM25 confidence score. Results cached 30 min.' — The verb 'Search' and the function of retrieving and returning cached results are characteristic of Read operations with no modification or…
Documented attack patterns abuse exactly the kind of access sicry_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sicry, and nothing reaches the server without passing your rules. This is the rule we recommend for sicry_search:
{
"version": "1",
"default": "deny",
"tools": {
"sicry_search": {}
}
}sicry_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search 12 .onion search engines. Results include BM25 confidence score. Results cached 30 min. It is categorised as a Read tool in the Sicry MCP Server, which means it retrieves data without modifying state.
Register the Sicry MCP server in PolicyLayer and add a rule for sicry_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Sicry. Nothing to install.
sicry_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sicry_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for sicry_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
sicry_search is provided by the Sicry MCP server (jacobjandon/sicry). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sicry, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
15 Sicry tools catalogued and risk-classified — across an index of 43,000+ MCP servers.