AI agents call get_users to retrieve information from Mantis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation as it queries and retrieves user data with no side effects. However, severity is high because: (1) the description indicates a brute-force or forceful retrieval method suggesting potential unauthorized access patterns, (2) retrieving all users at once exposes comprehensive user information that could enable further attacks (account enumeration, targeting specific users), and (3) in a bug…
From the tool's definition Tool name is 'get_users' and description states it retrieves all users (translated: 'forcefully obtain all users through brute force method'). The function retrieves user data without modifying it.
Attacks that exploit this kind of access
用暴力法強制取得所有用戶. It is categorised as a Read tool in the Mantis MCP Server, which means it retrieves data without modifying state.
Register the Mantis MCP server in PolicyLayer and add a rule for get_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 Mantis. Nothing to install.
get_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 get_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 get_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.
get_users is provided by the Mantis MCP server (mantis-mcp-server). 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 →