AI agents use discord_add_role 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.
This tool modifies Discord guild state by assigning roles to members. Role assignment is reversible (roles can be removed), so it falls under Write rather than Destructive. The severity is high because improper assignment could grant dangerous permissions (e.g., moderation, admin roles) to unintended members, with potential for abuse in moderation, access control, and guild governance.
From the tool's definition Tool description states: 'Assign an existing role to a member.' Assignment of roles is a reversible modification of member permissions and group membership.
Attacks that exploit this kind of access
Assign an existing role to a member. Requires the Manage Roles permission, and the role must be below the bot. 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 discord_add_role: 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.
discord_add_role 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 discord_add_role 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 discord_add_role. 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.
discord_add_role is provided by the Discord MCP server (@pasympa/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 →