AI agents call apitap_discover to retrieve information from ApiTap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Probing a site is a read-only reconnaissance action that queries what APIs or endpoints are available. It retrieves information about the target without side effects, state changes, or data modification. The low severity reflects minimal blast radius—discovering API endpoints does not execute operations, move money, or delete data.
From the tool's definition Tool name 'apitap_discover' with description 'Probe a site' indicates reconnaissance/discovery of available endpoints or information from a website without modifying data.
Documented attack patterns abuse exactly the kind of access apitap_discover gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ApiTap, and nothing reaches the server without passing your rules. This is the rule we recommend for apitap_discover:
{
"version": "1",
"default": "deny",
"tools": {
"apitap_discover": {}
}
}apitap_discover 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.
Probe a site\. It is categorised as a Read tool in the ApiTap MCP Server, which means it retrieves data without modifying state.
Register the ApiTap MCP server in PolicyLayer and add a rule for apitap_discover: 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 ApiTap. Nothing to install.
apitap_discover 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 apitap_discover 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 apitap_discover. 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.
apitap_discover is provided by the ApiTap MCP server (n1byn1kt/apitap). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ApiTap, 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.
12 ApiTap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.