AI agents use webhook_create to create or update resources in Mementos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mementos environment.
This tool creates a new persistent webhook resource, which is a Write operation—it modifies the system state by adding a new entity. Severity is high because webhooks can forward sensitive data or context to attacker-controlled URLs if an AI agent is manipulated into creating webhooks pointing to malicious endpoints.
From the tool's definition Tool name 'webhook_create' and description 'Create a persistent HTTP webhook hook' indicate irreversible creation of a new resource that persists in the system. The webhook will establish an ongoing communication channel that POSTs data to an external URL.
Attacks that exploit this kind of access
Create a persistent HTTP webhook hook. The URL will be POSTed with the hook context as JSON. It is categorised as a Write tool in the Mementos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mementos MCP server in PolicyLayer and add a rule for webhook_create: 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 Mementos. Nothing to install.
webhook_create 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 webhook_create 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 webhook_create. 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.
webhook_create is provided by the Mementos MCP server (@hasna/mementos). 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 →