AI agents call sicry_to_csv 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 exports/converts existing results into a CSV format string. It reads/transforms data already in memory and returns a string representation. No external side effects, no deletion, no execution. The Tor/dark web context of the server slightly elevates concern but the tool itself is a data formatting/export operation.
From the tool's definition Export results as CSV string
Documented attack patterns abuse exactly the kind of access sicry_to_csv 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_to_csv:
{
"version": "1",
"default": "deny",
"tools": {
"sicry_to_csv": {}
}
}sicry_to_csv 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.
Export results as CSV string. 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_to_csv: 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_to_csv 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_to_csv 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_to_csv. 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_to_csv 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.