AI agents call frage_vorbereiten 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.
This tool prepares question answering by searching and warning about data states—purely informational operations with no side effects. It fits the Read category: retrieves/queries data with no capacity to create, modify, delete, or execute external operations.
From the tool's definition The tool 'frage_vorbereiten' (prepare question) 'warnt bei unverarbeitetem RAW, liefert Suchtreffer' (warns about unprocessed RAW, delivers search results). It retrieves and queries data without modifying or deleting anything.
Attacks that exploit this kind of access
Bereitet die Beantwortung einer Frage vor: warnt bei unverarbeitetem RAW, liefert Suchtreffer,. 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 frage_vorbereiten: 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.
frage_vorbereiten 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 frage_vorbereiten 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 frage_vorbereiten. 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.
frage_vorbereiten 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 →