browser_login · Psamvault MCP: Risk & Policy

WHAT IT DOES

What browser_login does on Psamvault

AI agents invoke browser_login to trigger actions in Psamvault. 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 browser_login needs a policy

This tool executes a browser session and performs a login operation against an external site using stored credentials. It triggers real external operations (browser automation + network authentication), making it Execute category. Severity is high because misuse could authenticate into arbitrary sites on behalf of the user, potentially granting an AI agent access to sensitive accounts.

From the tool's definition "Open a visible browser and securely log into a site" — triggers an external browser action and performs authentication against a remote site

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

browser_login Rate-limited

browser_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": {
    "browser_login": {
      "limits": [
        {
          "counter": "browser_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 Psamvault, so you can run agents against it safely.

FAQ

Questions about browser_login

What does the browser_login tool do? +

[🔐 Site Authentication] Open a visible browser and securely log into a site using a stored psamvault credential. It is categorised as a Execute tool in the Psamvault MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_login? +

Register the Psamvault MCP server in PolicyLayer and add a rule for browser_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 Psamvault. Nothing to install.

What risk level is browser_login? +

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

Can I rate-limit browser_login? +

Yes. Add a rate_limit block to the browser_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 browser_login completely? +

Set action: deny in the PolicyLayer policy for browser_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 browser_login? +

browser_login is provided by the Psamvault MCP server (psam-717/psamvault-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.