AI agents call get_settings to retrieve information from Mullvad without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns current VPN settings in a read-only manner. It retrieves information about the system state (settings configuration) without creating, modifying, deleting, or executing operations. While settings data could be sensitive (revealing VPN configuration preferences), the tool itself performs no actions that could harm the system or data.
From the tool's definition Tool name 'get_settings' and description 'Get all current Mullvad VPN settings as a structured object' indicate retrieval of configuration data without modification or side effects.
Attacks that exploit this kind of access
Get all current Mullvad VPN settings as a structured object. It is categorised as a Read tool in the Mullvad MCP Server, which means it retrieves data without modifying state.
Register the Mullvad MCP server in PolicyLayer and add a rule for get_settings: 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 Mullvad. Nothing to install.
get_settings is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_settings 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 get_settings. 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.
get_settings is provided by the Mullvad MCP server (oresam-xyz/mullvad-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 →