generate_app_import
AI agents use generate_app_import to create or update resources in Veeam Ports — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Veeam Ports environment.
The tool generates firewall rule import files, which are written to the system for import. This constitutes data creation/modification (Write category). However, the severity is moderate rather than high because: (1) the actual import action is not performed by this tool (it only generates the file), and (2) firewall rule changes are reversible.
From the tool's definition Tool name 'generate_app_import' combined with server description stating it produces 'firewall rule import files'. The suffix 'app_import' suggests creating or generating importable data files.
Attacks that exploit this kind of access
generate_app_import. It is categorised as a Write tool in the Veeam Ports MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Veeam Ports MCP server in PolicyLayer and add a rule for generate_app_import: 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 Veeam Ports. Nothing to install.
generate_app_import 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 generate_app_import 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 generate_app_import. 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.
generate_app_import is provided by the Veeam Ports MCP server (shapedthought/veeam-ports-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 →