AI agents call get_cves to retrieve information from JamfMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves vulnerability information for analysis and monitoring purposes. While the description is empty, the name and context of Jamf Pro (a device management platform) suggest it fetches CVE data relevant to computer security assessment. This is consistent with other diagnostic and inventory retrieval tools on the server. No modification, execution, deletion, or financial action is implied.
From the tool's definition Tool name 'get_cves' indicates retrieval of CVE (Common Vulnerabilities and Exposures) data. Consistent with sibling tools like 'get_advanced_computer_search_details', 'get_basic_diagnostics', and 'get_computer_inventory' which are all read-only queries.
Attacks that exploit this kind of access
get_cves. It is categorised as a Read tool in the JamfMCP MCP Server, which means it retrieves data without modifying state.
Register the Jamf MCP server in PolicyLayer and add a rule for get_cves: 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 JamfMCP. Nothing to install.
get_cves 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_cves 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_cves. 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_cves is provided by the Jamf MCP server (liquidz00/jamfmcp). 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 →