proxy_authenticated_request · Authbox MCP: Risk & Policy

WHAT IT DOES

What proxy_authenticated_request does on Authbox

AI agents invoke proxy_authenticated_request to trigger actions in Authbox. 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 proxy_authenticated_request needs a policy

This tool executes arbitrary authenticated HTTP requests to external services. The credential injection means the agent can trigger any API action — including writes, deletes, or financial operations — on the target service, depending on the arguments supplied.

From the tool's definition 'Make an authenticated HTTP request through Auth Box' and 'The stored credential is injected into the request without exposing it to the agent'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

proxy_authenticated_request Rate-limited

proxy_authenticated_request 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": {
    "proxy_authenticated_request": {
      "limits": [
        {
          "counter": "proxy_authenticated_request_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 Authbox, so you can run agents against it safely.

FAQ

Questions about proxy_authenticated_request

What does the proxy_authenticated_request tool do? +

Make an authenticated HTTP request through Auth Box. The stored credential is injected into the request without exposing it to the agent. This is the preferred method for using credentials. It is categorised as a Execute tool in the Authbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on proxy_authenticated_request? +

Register the Authbox MCP server in PolicyLayer and add a rule for proxy_authenticated_request: 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 Authbox. Nothing to install.

What risk level is proxy_authenticated_request? +

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

Can I rate-limit proxy_authenticated_request? +

Yes. Add a rate_limit block to the proxy_authenticated_request 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 proxy_authenticated_request completely? +

Set action: deny in the PolicyLayer policy for proxy_authenticated_request. 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 proxy_authenticated_request? +

proxy_authenticated_request is provided by the Authbox MCP server (marucie/authbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.