search_ports
AI agents call search_ports to retrieve information from Veeam Ports without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches port requirements data without modifying, deleting, or executing external operations. It retrieves information to support infrastructure queries. While the description is empty, the server's documented purpose and naming convention of sibling tools strongly indicate this is a read operation.
From the tool's definition Tool named 'search_ports' on a server that 'Provides structured access to Veeam product network port requirements. Enables querying ports' — the core functionality is querying/retrieving port data.
Attacks that exploit this kind of access
search_ports. It is categorised as a Read tool in the Veeam Ports MCP Server, which means it retrieves data without modifying state.
Register the Veeam Ports MCP server in PolicyLayer and add a rule for search_ports: 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.
search_ports 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 search_ports 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 search_ports. 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.
search_ports 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 →