AI agents call get_patch_software_titles 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 a list of available patch software titles from Jamf Pro. It is a query/list operation that does not create, modify, delete, or execute any actions. The scope is informational only, presenting existing data about patch software inventory. Low severity due to minimal blast radius if misused—an AI agent calling this repeatedly would at worst generate verbose output or cause minor API load.
From the tool's definition Tool name 'get_patch_software_titles' and description 'Get list of all patch software titles' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get list of all patch software titles. 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_patch_software_titles: 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_patch_software_titles 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_patch_software_titles 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_patch_software_titles. 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_patch_software_titles 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 →