Set the Aarstiderne box URL to track
AI agents use set_box_url to create or update resources in Mcp Veggie — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Veggie environment.
The tool modifies a stored configuration parameter (the box URL) but does not delete data, execute external code, or trigger irreversible actions. It is a standard Write operation with minimal blast radius—a misconfigured URL would only affect data retrieval for this service, not cause financial loss or destructive outcomes.
From the tool's definition Tool name 'set_box_url' and description 'Set the Aarstiderne box URL to track' indicate creation or modification of a configuration setting (the box URL). This is reversible data modification.
Attacks that exploit this kind of access
Set the Aarstiderne box URL to track. It is categorised as a Write tool in the Mcp Veggie MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Veggie MCP server in PolicyLayer and add a rule for set_box_url: 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 Mcp Veggie. Nothing to install.
set_box_url 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_box_url 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_box_url. 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_box_url is provided by the Mcp Veggie MCP server (lovettbarron/mcp-veggiebox). 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 →