AI agents call destillat_auftrag to retrieve information from Lokyy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although this tool itself performs a read operation (listing and retrieving distillation instructions), its purpose within the broader system is to facilitate the distillation workflow. The actual writing/modification happens downstream, but this tool's role is informational and retrievals-based.
From the tool's definition The tool "listet unverarbeitete Quellen und liefert die Destillier-Anweisung" (lists unprocessed sources and provides distillation instructions). The primary function is listing/querying data about unprocessed sources, which is a retrieval operation.
Attacks that exploit this kind of access
Listet unverarbeitete Quellen und liefert die Destillier-Anweisung. Die Denkarbeit liegt beim Agenten; der Server validiert die Ergebnisse. It is categorised as a Read tool in the Lokyy MCP Server, which means it retrieves data without modifying state.
Register the Lokyy MCP server in PolicyLayer and add a rule for destillat_auftrag: 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 Lokyy. Nothing to install.
destillat_auftrag 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 destillat_auftrag 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 destillat_auftrag. 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.
destillat_auftrag is provided by the Lokyy MCP server (oliverhees/lokyy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →