remove_effect
AI agents call remove_effect to permanently remove resources in DM20 Protocol — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name suggests irreversibly removing an effect from a character or entity. Given sibling tools like 'apply_effect', this is the inverse operation — likely removing a status effect, buff, or debuff. Removal of data without undo capability maps to Destructive. However, the empty description lowers confidence; in some implementations effects may be re-applied, making it closer to Write.
From the tool's definition Tool name 'remove_effect' implies deletion/removal of an effect; description is empty and uninformative.
Attacks that exploit this kind of access
remove_effect. It is categorised as a Destructive tool in the DM20 Protocol MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the DM20 Protocol MCP server in PolicyLayer and add a rule for remove_effect: 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 DM20 Protocol. Nothing to install.
remove_effect 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_effect 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_effect. 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_effect is provided by the DM20 Protocol MCP server (polloinfilzato/dm20-protocol). 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 →