AI agents call monobank-get-webhook to retrieve information from Monobank without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves webhook configuration metadata. It performs a read-only operation with no side effects, no data modification, and no external triggering. The worst-case misuse is information disclosure of a webhook URL, which is low severity. It does not create, delete, modify, execute code, or move money.
From the tool's definition Tool 'monobank-get-webhook' 'Returns the webhook URL currently configured' — retrieves existing configuration without modification.
Attacks that exploit this kind of access
Returns the webhook URL currently configured for this Monobank token. Empty string means no webhook is set. It is categorised as a Read tool in the Monobank MCP Server, which means it retrieves data without modifying state.
Register the Monobank MCP server in PolicyLayer and add a rule for monobank-get-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 Monobank. Nothing to install.
monobank-get-webhook is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the monobank-get-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 monobank-get-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.
monobank-get-webhook is provided by the Monobank MCP server (todesstoss/monobank-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 →