// SCAN REPORT

Defined

38 tools. 26 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

26 can modify or destroy data

12 read-only

38 tools total

Community server · catalogue entry verified 29/06/2026

How to control Defined ↓

TOOL MAP

What Defined exposes to your agents

Read (12) Write / Execute (19) Destructive / Financial (7)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Defined tools

Destructive · High delete_host This tool permanently removes a host from the Defined Networking infrastructure. Destructive · High delete_role Deleting a role is a destructive action that cannot be undone—it permanently removes role definitions from the Defined Networking infrastructure. Destructive · High delete_route This tool performs an irreversible deletion operation on network routing configuration. Destructive · High delete_tag Deleting a tag is an irreversible operation that cannot be undone.

26 of Defined's 38 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Defined

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

Deny destructive operations

{
  "delete_host": {
    "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

{
  "add_firewall_rule": {
    "limits": [
      {
        "counter": "add_firewall_rule_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_host": {
    "limits": [
      {
        "counter": "get_host_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 Defined — 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 DEFINED →

Instant setup, no code required.

FULL CATALOGUE

All 38 Defined tools

DESTRUCTIVE 7 tools

Destructive delete_host Delete a host. Destructive delete_role Delete a role. Destructive delete_route Delete a route. Destructive delete_tag Delete a tag. Destructive remove_firewall_rule Remove a firewall rule from a role by its index. Use get_role to see current rules. Destructive remove_route_firewall_rule Remove a firewall rule from a route by index. Use get_route to see current rules. Destructive remove_tag_config_override Remove a config override from a tag by key.

WRITE 19 tools

Write add_firewall_rule add_firewall_rule Write add_host_tag Add a tag to a host. Preserves existing tags. Write add_route_firewall_rule add_route_firewall_rule Write add_tag_config_override add_tag_config_override Write block_host Block a host, preventing it from communicating on the network. Write create_enrollment_code Create an enrollment code for a host. Write create_host create_host Write create_host_and_enrollment_code create_host_and_enrollment_code Write create_network Create a network. Write create_role Create a role with firewall rules. Write create_route create_route Write create_tag create_tag Write remove_host_tag Remove a tag from a host. Preserves other tags. Write unblock_host Unblock a host, allowing it to rejoin the network. Write update_host update_host Write update_network Update a network. Full replacement. Write update_role update_role Write update_route update_route Write update_tag update_tag

READ 12 tools

Read get_host Get a host by ID. Read get_network Get a network by ID. Read get_role Get a role by ID, including its firewall rules. Read get_route Get a route by ID, including full firewall rules. Read get_tag Get a tag by name. Read list_audit_logs list_audit_logs Read list_downloads List available software downloads (unauthenticated). Read list_hosts list_hosts Read list_networks List networks. Read list_roles List roles. Read list_routes List routes (summary, without full firewall rules).

EXPLORE

Related servers

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

FAQ

Questions about Defined

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

Yes. The Defined server exposes 7 destructive tools including delete_host, delete_role, delete_route. 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 Defined? +

The Defined server has 19 write tools including add_firewall_rule, add_host_tag, add_route_firewall_rule. 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 Defined.

How many tools does the Defined MCP server expose? +

38 tools across 3 categories: Destructive, Read, Write. 12 are read-only. 26 can modify, create, or delete data.

How do I enforce a policy on Defined? +

Register the Defined 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 Defined tool call.

Deterministic rules across all 38 Defined tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEFINED →

Instant setup, no code required.

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