Unifi

31 tools. 14 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated:

14 can modify or destroy data
17 read-only
31 tools total

Community server · catalogue entry verified 29/06/2026

How to control Unifi ↓

What Unifi exposes to your agents

Read (17) Write / Execute (11) Destructive / Financial (3)
Critical Risk

The most dangerous Unifi tools

14 of Unifi's 31 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Unifi

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

Deny destructive operations
{
  "manage_firewall_policy": {
    "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
{
  "manage_acl_rule": {
    "limits": [
      {
        "counter": "manage_acl_rule_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_client": {
    "limits": [
      {
        "counter": "get_client_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Unifi — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON UNIFI →

Instant setup, no code required.

All 31 Unifi tools

READ 17 tools
Read get_client Get detailed info for a single connected client. Read get_device Get full details for a single adopted device including uplink topology, Read get_device_stats Get real-time performance statistics for a device: CPU utilization, memory usage, Read get_system_info Get UniFi Network application version and basic info. Read get_wan_status List WAN (internet uplink) interfaces with status, IP, and throughput. Read list_clients List all currently connected clients (wired, wireless, VPN, guest). Read list_devices List all adopted UniFi devices (APs, switches, gateways, etc.) with their state, Read list_dpi_apps List DPI (Deep Packet Inspection) application categories and applications. Read list_firewall_policies List all firewall policies with their source/destination zones, actions, and ordering. Read list_firewall_zones List all firewall zones. Zones group network interfaces for policy enforcement. Read list_known_clients List ALL historically known clients (not just currently connected) with rich metadata Read list_networks List all network configurations including VLAN IDs, DHCP settings, and status. Read list_pending_devices List devices discovered on the network but not yet adopted. Read list_sites List all UniFi sites on this controller. Read list_vpn List VPN tunnels and servers. Returns both site-to-site VPN tunnels Read list_wifi List all WiFi SSIDs (broadcasts) with their security config, data rates, Read search_actions Search the UniFi action catalog and return action IDs that can be executed via execute_action.

Related servers

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

Questions about Unifi

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

Yes. The Unifi server exposes 3 destructive tools including manage_firewall_policy, manage_network, manage_wifi. 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 Unifi? +

The Unifi server has 8 write tools including manage_acl_rule, manage_client, manage_device. 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 Unifi.

How many tools does the Unifi MCP server expose? +

31 tools across 3 categories: Execute, Read, Write. 17 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on Unifi? +

Register the Unifi 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 Unifi tool call.

Deterministic rules across all 31 Unifi tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.