probe_api · Mcp Public Apis MCP: Risk & Policy

WHAT IT DOES

What probe_api does on Mcp Public Apis

AI agents invoke probe_api to trigger actions in Mcp Public Apis. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why probe_api needs a policy

This tool executes real outbound HTTP requests to external endpoints. While described as 'safe' and read-only (GET), it triggers external network operations whose effects depend on the URL argument — qualifying as Execute. An agent could misuse this to probe internal/sensitive endpoints, cause unintended side effects on rate-limited APIs, or be used for reconnaissance.

From the tool's definition Makes a safe live HTTP GET request to a given API endpoint and returns the response status, shape, and latency.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

probe_api Rate-limited

probe_api stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "probe_api": {
      "limits": [
        {
          "counter": "probe_api_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Public Apis, so you can run agents against it safely.

FAQ

Questions about probe_api

What does the probe_api tool do? +

Makes a safe live HTTP GET request to a given API endpoint and returns the response status, shape, and latency. It is categorised as a Execute tool in the Mcp Public Apis MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on probe_api? +

Register the Mcp Public Apis MCP server in PolicyLayer and add a rule for probe_api: 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 Mcp Public Apis. Nothing to install.

What risk level is probe_api? +

probe_api is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit probe_api? +

Yes. Add a rate_limit block to the probe_api 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.

How do I block probe_api completely? +

Set action: deny in the PolicyLayer policy for probe_api. 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.

What MCP server provides probe_api? +

probe_api is provided by the Mcp Public Apis MCP server (josephsenior/pblic-apis-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.