Fetch any URL through Tor (.onion or clearnet). Returns title, text, links.
AI agents call sicry_fetch 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.
This tool retrieves and parses web content but does not modify, delete, or execute code. While the underlying Tor network enables access to hidden services on the dark web (which may host illegal content), the tool itself is a passive HTTP fetcher that reads and returns page metadata. The risk is informational access, not capability for harm—comparable to a standard web scraper or curl request.
From the tool's definition Tool description states it 'Fetch[es] any URL through Tor' and 'Returns title, text, links.' The verb 'fetch' and the returned data (title, text, links) indicate retrieval/query operations with no mention of modification, deletion, or execution of arbitrary…
Documented attack patterns abuse exactly the kind of access sicry_fetch 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_fetch:
{
"version": "1",
"default": "deny",
"tools": {
"sicry_fetch": {}
}
}sicry_fetch 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.
Fetch any URL through Tor (.onion or clearnet). Returns title, text, links. 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_fetch: 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_fetch 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_fetch 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_fetch. 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_fetch 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.