AI agents use modify_webhook 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 webhooks is a Write operation: it creates or changes webhook metadata reversibly. Unlike Execute tools that trigger external operations, or Destructive tools that delete, this modifies existing webhook settings. Severity is medium because misconfiguration could redirect messages or events to unintended destinations, but changes remain reversible.
From the tool's definition Tool description states 'Modify a webhook' — a reversible change operation that alters webhook configuration (URL, name, avatar, events, etc.) without deletion or execution of external code.
Attacks that exploit this kind of access
Modify a webhook. 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_webhook: 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_webhook 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_webhook 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_webhook. 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_webhook 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 →