login_start · Talon MCP: Risk & Policy

WHAT IT DOES

What login_start does on Talon

AI agents invoke login_start to trigger actions in Talon. 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 login_start needs a policy

This tool triggers an external operation (sending an email with a verification code) that has side effects outside the system. It is not a simple read, nor does it write/modify stored data directly. It executes an external action (email delivery) whose effect depends on the provided argument (email address). Misuse could spam users with verification emails or be used to enumerate valid accounts.

From the tool's definition Start login by sending a verification code to the given email address

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

login_start Rate-limited

login_start 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": {
    "login_start": {
      "limits": [
        {
          "counter": "login_start_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 Talon, so you can run agents against it safely.

FAQ

Questions about login_start

What does the login_start tool do? +

Start login by sending a verification code to the given email address. It is categorised as a Execute tool in the Talon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on login_start? +

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

What risk level is login_start? +

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

Can I rate-limit login_start? +

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

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

login_start is provided by the Talon MCP server (talon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.