Create a custom project role with Infisical permission rules.
AI agents use create_project_role to create or update resources in Infisical MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Infisical MCP environment.
This tool creates new project roles which modifies project configuration and access control settings. This is a Write operation (creates/adds new configuration data) rather than Read (retrieval only), Execute (arbitrary code execution), or Destructive (irreversible deletion).
From the tool's definition Tool description states 'Create a custom project role' - this is a reversible creation operation that modifies the access control configuration of a project by adding new role definitions with specified permission rules.
Attacks that exploit this kind of access
Create a custom project role with Infisical permission rules. It is categorised as a Write tool in the Infisical MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Infisical MCP server in PolicyLayer and add a rule for create_project_role: 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.
create_project_role is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_project_role 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 create_project_role. 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.
create_project_role 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 →