perform_login · MCP Login Server MCP: Risk & Policy

WHAT IT DOES

What perform_login does on MCP Login Server

AI agents invoke perform_login to trigger actions in MCP Login Server. 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 perform_login needs a policy

This tool executes browser automation actions (clicking, form filling, navigation) to authenticate against a web application. It triggers external operations via Playwright whose effects depend on the target application.

From the tool's definition 'Performs automated login' using 'browser automation' with 'predefined credentials (admin/AIWorkshopJuly!25)' against 'http://localhost'

Risk signalsAdmin/system-level operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

perform_login Rate-limited

perform_login 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": {
    "perform_login": {
      "limits": [
        {
          "counter": "perform_login_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 Login Server, so you can run agents against it safely.

FAQ

Questions about perform_login

What does the perform_login tool do? +

Performs automated login to http://localhost using predefined credentials (admin/AIWorkshopJuly!25). This tool requires a Playwright MCP server to be running for browser automation. It is categorised as a Execute tool in the MCP Login Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on perform_login? +

Register the MCP Login Server MCP server in PolicyLayer and add a rule for perform_login: 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 Login Server. Nothing to install.

What risk level is perform_login? +

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

Can I rate-limit perform_login? +

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

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

perform_login is provided by the MCP Login Server MCP server (nieperdragon/custom_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.