// SCAN REPORT

Project Creator MCP

28 tools. 22 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 4 Jul 2026

22 can modify or destroy data

6 read-only

28 tools total

Community server · catalogue entry verified 04/07/2026

How to control Project Creator MCP ↓

TOOL MAP

What Project Creator MCP exposes to your agents

Read (6) Write / Execute (21) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Project Creator MCP tools

Destructive · High delete_file The delete_file tool performs an irreversible deletion of file system data. Execute · Medium initialize_git_repository This tool triggers execution of git init or equivalent command-line operations. Execute · High run_command Despite the empty description, the tool name 'run_command' and the server's explicit mention of 'command execution capabilities' make it clear this tool executes external commands or shell operations. Execute · High run_database_command Database command execution is a form of Execute because it runs external operations (database queries/management) whose effects depend on the arguments provided.

22 of Project Creator MCP's 28 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Project Creator MCP

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

Deny destructive operations

{
  "delete_file": {
    "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

{
  "add": {
    "limits": [
      {
        "counter": "add_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_project_info": {
    "limits": [
      {
        "counter": "get_project_info_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 Project Creator MCP — 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 PROJECT CREATOR →

Instant setup, no code required.

FULL CATALOGUE

All 28 Project Creator MCP tools

DESTRUCTIVE 1 tools

Destructive delete_file Delete a file.

EXECUTE 13 tools

WRITE 8 tools

Write add Add two numbers Write copy_file_or_directory Copy a file or directory to a new location. Write create_directory Create a directory. Write create_file Create a file with specified content. Write create_project_structure create_project_structure Write search_and_replace_in_file search_and_replace_in_file Write update_project_state update_project_state Write write_file Write content to a file (alias for create_file).

READ 6 tools

Read get_project_info Get information about a project directory. Read get_project_state get_project_state Read get_tool_usage_guide Returns a guide for AI agents on how to use this MCP server's tools effectively. Read list_available_templates List all available project templates. Read list_directory List directory contents with detailed information. Read read_file Read file contents.

EXPLORE

Related servers

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

FAQ

Questions about Project Creator MCP

Can an AI agent delete data through the Project Creator MCP server? +

Yes. The Project Creator MCP server exposes 1 destructive tools including delete_file. 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 Project Creator MCP? +

The Project Creator MCP server has 8 write tools including add, copy_file_or_directory, create_directory. 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 Project Creator MCP.

How many tools does the Project Creator MCP server expose? +

28 tools across 4 categories: Destructive, Execute, Read, Write. 6 are read-only. 22 can modify, create, or delete data.

How do I enforce a policy on Project Creator MCP? +

Register the Project Creator 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 Project Creator MCP tool call.

Deterministic rules across all 28 Project Creator MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PROJECT CREATOR →

Instant setup, no code required.

28 Project Creator MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.