// SCAN REPORT

For Claudes Toolbox

16 tools. 4 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

4 can modify or destroy data

12 read-only

16 tools total

Community server · catalogue entry verified 29/06/2026

How to control For Claudes Toolbox ↓

TOOL MAP

What For Claudes Toolbox exposes to your agents

Read (12) Write / Execute (3) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous For Claudes Toolbox tools

Destructive · High delete_markdown_file delete_markdown_file Execute · Medium execute_query execute_query Execute · Medium execute_query_json execute_query_json Write · Medium save_markdown_directory save_markdown_directory

4 of For Claudes Toolbox's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control For Claudes Toolbox

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

Deny destructive operations

{
  "delete_markdown_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

{
  "save_markdown_directory": {
    "limits": [
      {
        "counter": "save_markdown_directory_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "describe_table": {
    "limits": [
      {
        "counter": "describe_table_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 For Claudes Toolbox — 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 FOR CLAUDES TOOLBOX →

Instant setup, no code required.

FULL CATALOGUE

All 16 For Claudes Toolbox tools

DESTRUCTIVE 1 tools

Destructive delete_markdown_file delete_markdown_file

EXECUTE 2 tools

Execute execute_query execute_query Execute execute_query_json execute_query_json

WRITE 1 tools

Write save_markdown_directory save_markdown_directory

READ 12 tools

Read describe_table describe_table Read extract_markdown_files extract_markdown_files Read find_table find_table Read get_database_info get_database_info Read get_markdown_file_content get_markdown_file_content Read get_markdown_stats get_markdown_stats Read get_query_history get_query_history Read get_table_columns get_table_columns Read get_table_sample get_table_sample Read get_table_types get_table_types Read list_databases list_databases Read list_markdown_files list_markdown_files

EXPLORE

Related servers

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

FAQ

Questions about For Claudes Toolbox

Can an AI agent delete data through the For Claudes Toolbox MCP server? +

Yes. The For Claudes Toolbox server exposes 1 destructive tools including delete_markdown_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 For Claudes Toolbox? +

The For Claudes Toolbox server has 1 write tools including save_markdown_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 For Claudes Toolbox.

How many tools does the For Claudes Toolbox MCP server expose? +

16 tools across 4 categories: Destructive, Execute, Read, Write. 12 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on For Claudes Toolbox? +

Register the For Claudes Toolbox 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 For Claudes Toolbox tool call.

Deterministic rules across all 16 For Claudes Toolbox tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FOR CLAUDES TOOLBOX →

Instant setup, no code required.

16 For Claudes Toolbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.