Soft-delete a lesson (mark as deprecated). The lesson will no longer be served to any user.
AI agents call remove_lesson to permanently remove resources in LinguaMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While technically a 'soft delete' (marking as deprecated rather than physically removing data), the effect is irreversible in practice from the user perspective — the lesson is immediately removed from all users' curriculum with no indication of an undo mechanism. This has a broad blast radius: misuse could silently remove lessons from all users simultaneously, disrupting the entire learning curriculum.
From the tool's definition Soft-delete a lesson (mark as deprecated). The lesson will no longer be served to any user.
Attacks that exploit this kind of access
Soft-delete a lesson (mark as deprecated). The lesson will no longer be served to any user. It is categorised as a Destructive tool in the LinguaMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lingua MCP server in PolicyLayer and add a rule for remove_lesson: 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 LinguaMCP. Nothing to install.
remove_lesson is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_lesson 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 remove_lesson. 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.
remove_lesson is provided by the Lingua MCP server (marsmanleo/linguamcp). 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 →