AI agents use create_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.
Creating a webhook is a reversible data modification operation—webhooks can be deleted and are not financial or destructive in nature. However, the severity is high because webhooks grant external services the ability to post messages to channels, potentially enabling spam, impersonation, or unintended message distribution if an AI agent creates one maliciously or with incorrect permissions.
From the tool's definition Tool creates a new webhook, which is a persistent resource creation action. The server description states it lets clients 'create webhooks' among other management actions. Webhooks are write operations that create new data/resources in Discord.
Attacks that exploit this kind of access
Create a new webhook for a Discord channel. 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 create_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.
create_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 create_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 create_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.
create_webhook is provided by the Discord MCP server (ngoctranfire/discord-mcp-server). 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 →