AI agents use artikel_schreiben to create or update resources in Lokyy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lokyy environment.
The tool creates or updates wiki articles in a knowledge base, which is a reversible write operation. No indication of deletion or financial action. Severity is medium because an AI agent could overwrite existing knowledge base content, but the requirement of an explicit 'aktualisieren=true' flag provides some guard against accidental overwrites.
From the tool's definition 'Legt einen Wiki-Artikel an oder aktualisiert ihn' (creates or updates a wiki article); 'aktualisieren=true nötig' indicates update requires explicit flag
Attacks that exploit this kind of access
Legt einen Wiki-Artikel an oder aktualisiert ihn (aktualisieren=true nötig). Der Server rendert das. It is categorised as a Write tool in the Lokyy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lokyy MCP server in PolicyLayer and add a rule for artikel_schreiben: 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.
artikel_schreiben is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the artikel_schreiben 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 artikel_schreiben. 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.
artikel_schreiben 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 →