Spider a .onion site depth-first. Extracts entities, stores in SQLite.
AI agents invoke sicry_crawl to trigger actions in Sicry. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool actively crawls .onion (dark web) sites, executing a depth-first spider operation and writing extracted data to a SQLite database. It spans Execute (running a web crawler over Tor) and Write (storing data in SQLite). The most severe applicable category is Execute.
From the tool's definition Spider a .onion site depth-first. Extracts entities, stores in SQLite.
Documented attack patterns abuse exactly the kind of access sicry_crawl 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_crawl:
{
"version": "1",
"default": "deny",
"tools": {
"sicry_crawl": {
"limits": [
{
"counter": "sicry_crawl_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}sicry_crawl stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Spider a .onion site depth-first. Extracts entities, stores in SQLite. It is categorised as a Execute tool in the Sicry MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sicry MCP server in PolicyLayer and add a rule for sicry_crawl: 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_crawl is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sicry_crawl 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_crawl. 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_crawl 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.