start_browser_auth · Meducate MCP: Risk & Policy

WHAT IT DOES

What start_browser_auth does on Meducate MCP

AI agents invoke start_browser_auth to trigger actions in Meducate MCP. 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 start_browser_auth needs a policy

This tool executes a browser-based authentication workflow, which constitutes an Execute action rather than Read (it performs an operation, not just retrieval) or Write (it commits identity/session state rather than just modifying data). Severity is medium because OAuth misuse could grant unauthorized access to user accounts, but the tool itself doesn't directly modify data or transfer funds.

From the tool's definition Tool initiates an OAuth flow and returns a URL to open, triggering an external authentication operation via browser. This is an automated external operation (browser action) whose effects depend on user interaction with the returned URL.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_browser_auth Rate-limited

start_browser_auth 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": {
    "start_browser_auth": {
      "limits": [
        {
          "counter": "start_browser_auth_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 Meducate MCP, so you can run agents against it safely.

FAQ

Questions about start_browser_auth

What does the start_browser_auth tool do? +

Start a browser-based OAuth flow and return a URL to open. It is categorised as a Execute tool in the Meducate MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_browser_auth? +

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

What risk level is start_browser_auth? +

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

Can I rate-limit start_browser_auth? +

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

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

start_browser_auth is provided by the Meducate MCP server (joshnuku/meducate-mcp-demo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.