// SCAN REPORT

Infrastructure Auto Provisioner

33 tools. 11 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 5 Jul 2026

11 can modify or destroy data

22 read-only

33 tools total

Community server · catalogue entry verified 05/07/2026

How to control Infrastructure Auto Provisioner ↓

TOOL MAP

What Infrastructure Auto Provisioner exposes to your agents

Read (22) Write / Execute (9) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Infrastructure Auto Provisioner tools

Destructive · Critical destroy_plm_project_infrastructure This tool destroys project infrastructure, which is an irreversible operation that cannot be undone. Destructive · Critical destroy_tf_project_infrastructure This tool destroys infrastructure (likely Terraform-managed cloud resources), which is an irreversible operation that cannot be undone. Execute · High preview_plm_project While 'preview' is nominally read-only (it does not apply changes), it executes Pulumi code that could have side effects depending on the project contents and stack state. Execute · High apply_plm_project_infrastructure The tool name contains 'apply' which in infrastructure contexts (like Terraform) means provisioning or modifying cloud resources.

11 of Infrastructure Auto Provisioner's 33 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Infrastructure Auto Provisioner

PolicyLayer is an MCP gateway — it sits between your AI agents and Infrastructure Auto Provisioner, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "destroy_plm_project_infrastructure": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "initialize_plm_project": {
    "limits": [
      {
        "counter": "initialize_plm_project_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_plm_project_git_clone_url": {
    "limits": [
      {
        "counter": "get_plm_project_git_clone_url_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Infrastructure Auto Provisioner — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON INFRASTRUCTURE AUTO PROVISIONER →

Instant setup, no code required.

FULL CATALOGUE

All 33 Infrastructure Auto Provisioner tools

DESTRUCTIVE 2 tools

Destructive destroy_plm_project_infrastructure Run Destructive destroy_tf_project_infrastructure Run

EXECUTE 5 tools

Execute apply_plm_project_infrastructure Run Execute apply_tf_project_infrastructure Run Execute install_plm_project_dependency Install pulumi infrastructure project dependency Execute plan_tf_project_infrastructure Run Execute preview_plm_project Run pulumi preview for a given project and stack

WRITE 4 tools

Write initialize_plm_project Create a new pulumi infrastructure project Write initialize_tf_project Create a new terraform infrastructure project Write write_plm_configuration Write a pulumi configuration file Write write_tf_configuration Write a terraform configuration file

READ 22 tools

Read get_plm_project_git_clone_url Get a git-cloneable url for a pulumi project Read get_plm_resource Get information about a specific resource from the Pulumi Registry Read get_provider_tf_information Get high level provider terraform documentation Read get_tf_project_example_directory Get an example terraform configuration directory Read get_tf_project_example_directory_file Get a file from an example terraform configuration directory Read get_tf_project_git_clone_url Get a git-cloneable url for a terraform project Read get_tf_provider_resource_schema_details Get terraform provider resource schema details documentation Read list_plm_projects list pulumi projects Read list_plm_resources List all resource types for a given provider and module Read list_tf_project_examples List example terraform configuration directories Read list_tf_projects list terraform projects Read list_tf_provider_resource_schemas List terraform provider resource schemas documentation Read list_tf_provider_sources List terraform provider sources documentation Read poll_plm_project_infrastructure_job Check the status of an infrastructure job Read poll_tf_project_infrastructure_job Check the status of an infrastructure job Read read_github_project_file Read the contents of a GitHub project file Read read_github_project_fs Read the top-level files of a GitHub project Read read_plm_project_file Read the contents of a pulumi project file Read read_plm_project_fs Read the top-level files of a pulumi project Read read_tf_project_file Read the contents of a terraform project file Read read_tf_project_fs Read the top-level files of a terraform project Read search_tf_providers Search for terraform registry documentation describing a provider

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Infrastructure Auto Provisioner

Can an AI agent delete data through the Infrastructure Auto Provisioner MCP server? +

Yes. The Infrastructure Auto Provisioner server exposes 2 destructive tools including destroy_plm_project_infrastructure, destroy_tf_project_infrastructure. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Infrastructure Auto Provisioner? +

The Infrastructure Auto Provisioner server has 4 write tools including initialize_plm_project, initialize_tf_project, write_plm_configuration. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Infrastructure Auto Provisioner.

How many tools does the Infrastructure Auto Provisioner MCP server expose? +

33 tools across 4 categories: Destructive, Execute, Read, Write. 22 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Infrastructure Auto Provisioner? +

Register the Infrastructure Auto Provisioner MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Infrastructure Auto Provisioner tool call.

Deterministic rules across all 33 Infrastructure Auto Provisioner tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON INFRASTRUCTURE AUTO PROVISIONER →

Instant setup, no code required.

33 Infrastructure Auto Provisioner tools catalogued and risk-classified — across an index of 43,000+ MCP servers.