AI agents use modify_sticker to create or update resources in Discord — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Discord environment.
Modifying a sticker is a Write operation—it changes server data but remains reversible (can be modified again or restored). It is not Destructive (sticker is not deleted), Execute (no arbitrary code/commands), or Financial. The medium severity reflects that misuse could affect server customization and user experience, but the blast radius is limited to sticker management within a single server.
From the tool's definition Tool name 'modify_sticker' and description 'Modify a custom sticker in a server' indicate reversible modification of sticker data/properties.
Attacks that exploit this kind of access
Modify a custom sticker in a server. It is categorised as a Write tool in the Discord MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Discord MCP server in PolicyLayer and add a rule for modify_sticker: 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 Discord. Nothing to install.
modify_sticker 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 modify_sticker 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 modify_sticker. 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.
modify_sticker is provided by the Discord MCP server (scarecr0w12/discord-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 →