AI agents use set_location to create or update resources in Mullvad — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mullvad environment.
Based on the server description mentioning 'switch locations' and sibling tools like list_countries/list_cities/list_servers, set_location almost certainly changes the VPN exit node/location. This is a reversible configuration change (Write), not destructive or financial. Severity is medium because changing VPN location could affect network routing and privacy posture, but it can be easily reversed.
From the tool's definition Tool name 'set_location' on a VPN server — description is empty, so inferring from name and server context (Mullvad VPN location switching).
Attacks that exploit this kind of access
set_location. It is categorised as a Write tool in the Mullvad MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mullvad MCP server in PolicyLayer and add a rule for set_location: 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.
set_location 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 set_location 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 set_location. 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.
set_location 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 →