createDeviceApprove

Approve a device grant. OR Approve a device grant.

SERVERFusionauth SOURCE@fusionauth/mcp-api

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-fusionauth-mcp-api/createdeviceapprove.md

WHAT IT DOES

What createDeviceApprove does on Fusionauth

AI agents use createDeviceApprove to create or update resources in Fusionauth, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fusionauth environment.

RISK

Why createDeviceApprove is rated Medium

The tool modifies device grant state by approving it, which is a reversible change to data (the approval can presumably be revoked or the device managed separately). This is categorized as Write rather than Execute because it specifically approves a pre-existing device grant request rather than executing arbitrary code.

From the tool's definition Tool name 'createDeviceApprove' and description 'Approve a device grant' indicates the tool creates or modifies an approval state for a device grant. This is a write operation that changes authentication/device state.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs createDeviceApprove safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Fusionauth, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For createDeviceApprove, this is the rule to start with:

createDeviceApprove Rate-limited

createDeviceApprove stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "createDeviceApprove": {
      "limits": [
        {
          "counter": "createdeviceapprove_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Fusionauth, apply this rule, and every createDeviceApprove call is checked against it from then on.

FAQ

Questions about createDeviceApprove

What does the createDeviceApprove tool do? +

Approve a device grant. OR Approve a device grant. It is categorised as a Write tool in the Fusionauth MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on createDeviceApprove? +

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

What risk level is createDeviceApprove? +

createDeviceApprove is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit createDeviceApprove? +

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

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

createDeviceApprove is provided by the Fusionauth MCP server (@fusionauth/mcp-api). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Fusionauth, and thousands of servers like it.

This server

All 314 Fusionauth tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →