claude_login · Claude Usage MCP Server MCP: Risk & Policy

WHAT IT DOES

What claude_login does on Claude Usage MCP Server

AI agents invoke claude_login to trigger actions in Claude Usage 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 claude_login needs a policy

This tool triggers an external browser operation (opening a browser window) to perform authentication. It executes an action in the environment whose effects depend on user interaction and credentials. It is not a simple read, but an external operation trigger, placing it in the Execute category. Misuse could initiate unwanted authentication flows or session hijacking attempts.

From the tool's definition Open a browser window to authenticate with Claude

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

claude_login Rate-limited

claude_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": {
    "claude_login": {
      "limits": [
        {
          "counter": "claude_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 Claude Usage MCP Server, so you can run agents against it safely.

FAQ

Questions about claude_login

What does the claude_login tool do? +

Open a browser window to authenticate with Claude. Use this if get_claude_usage fails due to authentication. It is categorised as a Execute tool in the Claude Usage 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 claude_login? +

Register the Claude Usage MCP Server MCP server in PolicyLayer and add a rule for claude_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 Claude Usage MCP Server. Nothing to install.

What risk level is claude_login? +

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

Can I rate-limit claude_login? +

Yes. Add a rate_limit block to the claude_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 claude_login completely? +

Set action: deny in the PolicyLayer policy for claude_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 claude_login? +

claude_login is provided by the Claude Usage MCP Server MCP server (mvacaporale/claude-usage-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.