Create a new Firefox Relay random mask.
AI agents use relay_create_random_mask to create or update resources in Firefox Relay — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Firefox Relay environment.
Creating a Firefox Relay mask is a write operation that generates new data. While it modifies the user's email alias configuration, the action is reversible (masks can be disabled via relay_disable_random_mask), so it does not qualify as destructive.
From the tool's definition Tool name contains 'create' and description states 'Create a new Firefox Relay random mask', indicating it creates new data (email masks). This is reversible via the sibling tool 'relay_disable_random_mask'.
Attacks that exploit this kind of access
Create a new Firefox Relay random mask. It is categorised as a Write tool in the Firefox Relay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Firefox Relay MCP server in PolicyLayer and add a rule for relay_create_random_mask: 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 Firefox Relay. Nothing to install.
relay_create_random_mask is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the relay_create_random_mask 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.
Set action: deny in the PolicyLayer policy for relay_create_random_mask. 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.
relay_create_random_mask is provided by the Firefox Relay MCP server (nazar256/firefox-relay-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →