AI agents call get_projects 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 retrieves project information without modifying any data. It has no side effects and follows the Read category pattern of data retrieval operations (get, list, fetch). The blast radius if misused by an AI agent is minimal—it only exposes project metadata that would typically be accessible to authenticated users.
From the tool's definition Tool name is 'get_projects' and description indicates it retrieves/lists Mantis projects ('獲取 Mantis 專案列表' translates to 'Get Mantis projects list'). This is a query operation with no data modification.
Attacks that exploit this kind of access
獲取 Mantis 專案列表. 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_projects: 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_projects 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_projects 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_projects. 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_projects 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 →