// SCAN REPORT

Global MCP Manager

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

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

Last updated: 4 Jul 2026

7 can modify or destroy data

5 read-only

12 tools total

Community server · catalogue entry verified 04/07/2026

How to control Global MCP Manager ↓

TOOL MAP

What Global MCP Manager exposes to your agents

Read (5) Write / Execute (6) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Global MCP Manager tools

Destructive · Critical terminal_remove Despite the empty description, the tool name 'terminal_remove' combined with the server's documented file management capabilities and multi-environment scope (local, SSH, GitHub) indicates this tool deletes files or dire Execute · Medium terminal_cd The tool name 'terminal_cd' strongly suggests a change-directory operation in a terminal context. Execute · Critical terminal_exec The tool name 'terminal_exec' strongly implies executing terminal/shell commands. Write · High terminal_rename Renaming files is a Write operation—it modifies data (filenames/paths) reversibly.

7 of Global MCP Manager's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Global MCP Manager

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

Deny destructive operations

{
  "terminal_remove": {
    "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

{
  "set_context": {
    "limits": [
      {
        "counter": "set_context_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_config": {
    "limits": [
      {
        "counter": "get_config_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 Global MCP Manager — 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 GLOBAL MCP MANAGER →

Instant setup, no code required.

FULL CATALOGUE

All 12 Global MCP Manager tools

DESTRUCTIVE 1 tools

Destructive terminal_remove terminal_remove

EXECUTE 2 tools

Execute terminal_cd terminal_cd Execute terminal_exec terminal_exec

WRITE 4 tools

Write set_context set_context Write terminal_mkdir terminal_mkdir Write terminal_rename terminal_rename Write terminal_write_file terminal_write_file

READ 5 tools

Read get_config get_config Read terminal_exists terminal_exists Read terminal_list_dir terminal_list_dir Read terminal_pwd terminal_pwd Read terminal_read_file terminal_read_file

EXPLORE

Related servers

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

FAQ

Questions about Global MCP Manager

Can an AI agent delete data through the Global MCP Manager MCP server? +

Yes. The Global MCP Manager server exposes 1 destructive tools including terminal_remove. 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 Global MCP Manager? +

The Global MCP Manager server has 4 write tools including set_context, terminal_mkdir, terminal_rename. 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 Global MCP Manager.

How many tools does the Global MCP Manager MCP server expose? +

12 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Global MCP Manager? +

Register the Global MCP Manager 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 Global MCP Manager tool call.

Deterministic rules across all 12 Global MCP Manager tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON GLOBAL MCP MANAGER →

Instant setup, no code required.

12 Global MCP Manager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.