AI agents call get_users_by_project_id 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 tool queries and retrieves user information associated with a project. It performs a read-only operation that returns data without creating, modifying, deleting, or executing any actions. The blast radius is minimal—unauthorized access to user lists is a confidentiality concern but does not enable destructive or financial harm directly.
From the tool's definition Tool name 'get_users_by_project_id' and description '獲取指定專案的所有用戶' (Get all users for a specified project) indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
獲取指定專案的所有用戶. 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_by_project_id: 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_by_project_id 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_by_project_id 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_by_project_id. 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_by_project_id 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 →