AI agents call jira_search_users to retrieve information from Jiraxmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/query operation to retrieve user information from Jira. It does not create, modify, delete, execute code, or move money. The verb 'search' and the passive data retrieval nature confirm it as a Read operation. Severity is low because user directory information is typically non-sensitive in most organizational contexts, and the blast radius of an AI agent searching users is minimal.
From the tool's definition Tool name 'jira_search_users' and description 'Search Jira users by query or account id' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Search Jira users by query or account id. It is categorised as a Read tool in the Jiraxmcp MCP Server, which means it retrieves data without modifying state.
Register the Jirax MCP server in PolicyLayer and add a rule for jira_search_users: 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 Jiraxmcp. Nothing to install.
jira_search_users 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 jira_search_users 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 jira_search_users. 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.
jira_search_users is provided by the Jirax MCP server (vaibhavpandeyvpz/jiraxmcp). 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 →