// SCAN REPORT

Dev

7 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 31 Jul 2026

3 can modify or destroy data

4 read-only

7 tools total

Community server · catalogue entry checked 05/04/2026 · full schemas captured for 7 of 7 tools

How to control Dev ↓

TOOL MAP

What Dev exposes to your agents

Read (4) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Dev tools

Write · Low create_directory This tool creates new directories within the configured root. Write · Medium move_file Moving or renaming files modifies their paths and metadata but does not destroy data or create new persistent state that cannot be undone. Write · Medium write_file The tool modifies data reversibly by creating or overwriting files.

3 of Dev's 7 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Dev

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

Rate limit write operations

{
  "create_directory": {
    "limits": [
      {
        "counter": "create_directory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_file_info": {
    "limits": [
      {
        "counter": "get_file_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 Dev — 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 DEV →

Instant setup, no code required.

FULL CATALOGUE

All 7 Dev tools

WRITE 3 tools

Write create_directory Create a directory. Creates parent directories if they don't exist. Write move_file Move or rename a file or directory Write write_file Write content to a file. Creates the file if it doesn't exist, overwrites if it does.

READ 4 tools

Read get_file_info Get detailed information about a file or directory (size, permissions, timestamps, etc.) Read list_directory List files and directories in a specified path Read read_text_file Read a text file from the filesystem. Returns the file content as text. Read search_files Recursively search for files and directories matching a pattern

FAQ

Questions about Dev

How do I prevent bulk modifications through Dev? +

The Dev server has 3 write tools including create_directory, move_file, write_file. 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 Dev.

How many tools does the Dev MCP server expose? +

7 tools across 2 categories: Read, Write. 4 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Dev? +

Register the Dev 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 Dev tool call.

Deterministic rules across all 7 Dev tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEV →

Instant setup, no code required.

7 Dev tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Dev's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →