auth_login · Evaluar MCP Server MCP: Risk & Policy

WHAT IT DOES

What auth_login does on Evaluar MCP Server

AI agents invoke auth_login to trigger actions in Evaluar MCP 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 auth_login needs a policy

Authentication involves executing an external operation against the Evaluar platform (submitting credentials, establishing a session/token). It is not a simple read, nor does it write/modify user data, but it triggers an external session creation. Misuse could expose credentials or create unauthorized sessions, warranting medium severity.

From the tool's definition Authenticate with Evaluar using username and password. Returns success status and masked token info.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

auth_login Rate-limited

auth_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": {
    "auth_login": {
      "limits": [
        {
          "counter": "auth_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 Evaluar MCP Server, so you can run agents against it safely.

FAQ

Questions about auth_login

What does the auth_login tool do? +

Authenticate with Evaluar using username and password. Returns success status and masked token info. It is categorised as a Execute tool in the Evaluar MCP 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 auth_login? +

Register the Evaluar MCP Server MCP server in PolicyLayer and add a rule for auth_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 Evaluar MCP Server. Nothing to install.

What risk level is auth_login? +

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

Can I rate-limit auth_login? +

Yes. Add a rate_limit block to the auth_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 auth_login completely? +

Set action: deny in the PolicyLayer policy for auth_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 auth_login? +

auth_login is provided by the Evaluar MCP Server MCP server (yarmijosp94/evaluar-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.