Read the top-level files of a pulumi project
AI agents call read_plm_project_fs to retrieve information from Infrastructure Auto Provisioner without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file content from a Pulumi project directory without modifying, executing, or destructively removing any data. It is a straightforward read operation on infrastructure-as-code configuration files, presenting minimal risk to system integrity.
From the tool's definition Tool name contains 'read' and description states 'Read the top-level files of a pulumi project', indicating file system retrieval with no modification or execution.
Attacks that exploit this kind of access
Read the top-level files of a pulumi project. It is categorised as a Read tool in the Infrastructure Auto Provisioner MCP Server, which means it retrieves data without modifying state.
Register the Infrastructure Auto Provisioner MCP server in PolicyLayer and add a rule for read_plm_project_fs: 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 Infrastructure Auto Provisioner. Nothing to install.
read_plm_project_fs 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 read_plm_project_fs 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 read_plm_project_fs. 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.
read_plm_project_fs is provided by the Infrastructure Auto Provisioner MCP server (zerosync-co/mcp-server-autoprovisioner). 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 →