Quick check if any OOB (Out-of-Band) callbacks have been received. Useful for bug bounty to verify if SSRF, XXE, or blind injection payloads were triggered.
AI agents call check_for_callbacks to retrieve information from Webhook Site MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and inspects status information about received callbacks on a webhook endpoint. It has no side effects, does not modify data, execute code, or trigger external actions. While the broader server context involves security testing (bug bounty, SSRF, XXE detection), this specific tool is purely observational.
From the tool's definition Tool description states it performs a 'Quick check if any OOB callbacks have been received' — a query/retrieval operation that inspects data without modification, deletion, or execution.
Documented attack patterns abuse exactly the kind of access check_for_callbacks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Webhook Site MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for check_for_callbacks:
{
"version": "1",
"default": "deny",
"tools": {
"check_for_callbacks": {}
}
}check_for_callbacks is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Quick check if any OOB (Out-of-Band) callbacks have been received. Useful for bug bounty to verify if SSRF, XXE, or blind injection payloads were triggered. It is categorised as a Read tool in the Webhook Site MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Webhook Site MCP Server MCP server in PolicyLayer and add a rule for check_for_callbacks: 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 Webhook Site MCP Server. Nothing to install.
check_for_callbacks 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 check_for_callbacks 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 check_for_callbacks. 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.
check_for_callbacks is provided by the Webhook Site MCP Server MCP server (zebbern/webhook-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Webhook Site MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
23 Webhook Site MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.