// SCAN REPORT

Central

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

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

Last updated: 29 Jun 2026

3 can modify or destroy data

22 read-only

25 tools total

Community server · catalogue entry verified 29/06/2026

How to control Central ↓

TOOL MAP

What Central exposes to your agents

Read (22) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Central tools

Execute · High central_run_network_test This tool executes network tests against HPE Aruba infrastructure, which constitutes running operations with side effects that depend on arguments (e.g., which network segment, device, or test type to run). Execute · High central_run_show_commands The tool permits running show commands against network infrastructure (sites, devices, clients, alerts, events per server description). Execute · High central_bounce_port 'Bouncing' a port is a well-known network operations action that disables and re-enables a switch/AP port, causing connected devices to lose and re-establish connectivity.

3 of Central's 25 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Central

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

Cap read operations

{
  "central_find_client": {
    "limits": [
      {
        "counter": "central_find_client_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 Central — 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 CENTRAL →

Instant setup, no code required.

FULL CATALOGUE

All 25 Central tools

EXECUTE 3 tools

Execute central_bounce_port central_bounce_port Execute central_run_network_test central_run_network_test Execute central_run_show_commands central_run_show_commands

READ 22 tools

Read central_find_client central_find_client Read central_find_device central_find_device Read central_get_alerts central_get_alerts Read central_get_ap_details central_get_ap_details Read central_get_ap_trends central_get_ap_trends Read central_get_aps central_get_aps Read central_get_clients central_get_clients Read central_get_cluster_capacity_trends central_get_cluster_capacity_trends Read central_get_devices central_get_devices Read central_get_events central_get_events Read central_get_events_count central_get_events_count Read central_get_gateway_cluster central_get_gateway_cluster Read central_get_gateway_details central_get_gateway_details Read central_get_gateway_trends central_get_gateway_trends Read central_get_gateways central_get_gateways Read central_get_sites central_get_sites Read central_get_summary central_get_summary Read central_get_switch_details central_get_switch_details Read central_get_switch_trends central_get_switch_trends Read central_get_switches central_get_switches Read central_get_wlan_stats central_get_wlan_stats Read central_get_wlans central_get_wlans

EXPLORE

Related servers

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

FAQ

Questions about Central

Is the Central MCP server safe to use without restrictions? +

The Central server is primarily read-only with 22 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Central MCP server expose? +

25 tools across 2 categories: Execute, Read. 22 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Central? +

Register the Central 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 Central tool call.

Deterministic rules across all 25 Central tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CENTRAL →

Instant setup, no code required.

25 Central tools catalogued and risk-classified — across an index of 43,000+ MCP servers.