High Risk →

request_device_auth

Start a headless Google sign-in. Call this FIRST if you don't have an API token yet. Returns a user_code and verification_url for the user to visit, plus a device_code to use with poll_device_auth. No Bearer token required.

Part of the Mkdshare DEV server.

request_device_auth can trigger actions in Mkdshare DEV, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE MKDSHARE DEV →

Free to start. No card required.

AI agents invoke request_device_auth to trigger processes or run actions in Mkdshare DEV. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

request_device_auth can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "request_device_auth": {
      "limits": [
        {
          "counter": "request_device_auth_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Mkdshare DEV policy for all 10 tools.

Get this rule live on your own Mkdshare DEV server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY MKDSHARE DEV →

View all 10 tools →

These attack patterns abuse exactly the kind of access request_device_auth gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so request_device_auth only ever does what you allow.

SECURE MKDSHARE DEV →

Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the request_device_auth tool do? +

Start a headless Google sign-in. Call this FIRST if you don't have an API token yet. Returns a user_code and verification_url for the user to visit, plus a device_code to use with poll_device_auth. No Bearer token required.. It is categorised as a Execute tool in the Mkdshare DEV MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on request_device_auth? +

Register the Mkdshare DEV MCP server in PolicyLayer and add a rule for request_device_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 Mkdshare DEV. Nothing to install.

What risk level is request_device_auth? +

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

Can I rate-limit request_device_auth? +

Yes. Add a rate_limit block to the request_device_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 request_device_auth completely? +

Set action: deny in the PolicyLayer policy for request_device_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 request_device_auth? +

request_device_auth is provided by the Mkdshare DEV MCP server (https://mkdshare.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mkdshare DEV tool call.

Deterministic rules across all 10 Mkdshare DEV tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.