List custom project roles.
AI agents call list_project_roles to retrieve information from Infisical MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and enumerates existing project roles without creating, modifying, or deleting any data. It is a read-only operation that merely displays information, making it a Read category risk with low severity since it only accesses metadata about role definitions without exposing secret values or enabling unauthorized actions.
From the tool's definition Tool name is 'list_project_roles' and description states 'List custom project roles' — this is a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List custom project roles. It is categorised as a Read tool in the Infisical MCP MCP Server, which means it retrieves data without modifying state.
Register the Infisical MCP server in PolicyLayer and add a rule for list_project_roles: 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 Infisical MCP. Nothing to install.
list_project_roles 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 list_project_roles 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 list_project_roles. 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.
list_project_roles is provided by the Infisical MCP server (plgonzalezrx8/infisicalmcp). 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 →