AI agents use madeonsol_create_webhook to create or update resources in Madeonsol — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Madeonsol environment.
The tool creates (registers) a new webhook endpoint for push notifications. This is a Write action because it modifies system state by adding a new notification destination, not a destructive delete or irreversible change.
From the tool's definition Tool description states 'Register a webhook URL' — this creates a new webhook configuration, which is a reversible write operation that modifies the user's subscription settings or notification preferences.
Attacks that exploit this kind of access
Register a webhook URL to receive real-time push notifications for KOL trades and deployer alerts. Requires Pro/Ultra subscription. It is categorised as a Write tool in the Madeonsol MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Madeonsol MCP server in PolicyLayer and add a rule for madeonsol_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 Madeonsol. Nothing to install.
madeonsol_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 madeonsol_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 madeonsol_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.
madeonsol_create_webhook is provided by the Madeonsol MCP server (mcp-server-madeonsol). 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 →