AI agents call wissensbasis_durchsuchen 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.
The tool performs semantic search and information retrieval only. It searches existing knowledge bases and returns matching results (excerpts, file locations, line numbers). There are no side effects, no data modification, no code execution, and no destructive operations. This is a straightforward Read category tool with low severity risk.
From the tool's definition Tool description states 'Volltextsuche über Wiki (zuerst) und RAW. Liefert Datei, Zeile und Auszug' (full-text search over Wiki and RAW. Returns file, line, and excerpt).
Attacks that exploit this kind of access
Volltextsuche über Wiki (zuerst) und RAW. Liefert Datei, Zeile und Auszug. 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 wissensbasis_durchsuchen: 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.
wissensbasis_durchsuchen 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 wissensbasis_durchsuchen 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 wissensbasis_durchsuchen. 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.
wissensbasis_durchsuchen 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 →