firewall
Firewall: iptables, UFW, nftables, persistence, policy audit
This record as markdown: /tools/defense/firewall.md
What firewall does on Defense
AI agents invoke firewall to trigger actions in Defense. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
ipv6 | boolean | — | Also apply to ip6tables |
port | string | — | Port or range, e.g. '80', '8080:8090' |
chain | string | — | Target chain (INPUT, OUTPUT, FORWARD, or custom) |
table | string | — | Iptables/nftables table name |
action | string | Yes | Firewall action |
family | string | — | nftables address family |
policy | string | — | Default chain policy |
source | string | — | Source IP/CIDR |
dry_run | boolean | — | Preview without applying |
to_addr | string | — | Destination address or 'any' |
verbose | boolean | — | Show verbose output |
position | number | — | Rule insert position |
Parameters from the server's own tool schema.
Why firewall is rated High
Managing firewall rules via iptables, UFW, or nftables involves executing system-level commands that modify active network policy. Adding, removing, or changing rules affects live traffic filtering. 'Persistence' implies writing rules that survive reboots.
From the tool's definition Firewall: iptables, UFW, nftables, persistence, policy audit
Risk signalsAccepts file system path (destination) · High parameter count (27 properties)
Attacks that exploit this kind of access
The rule that runs firewall safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Defense, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For firewall, this is the rule to start with:
firewall stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Defense, apply this rule, and every firewall call is checked against it from then on.
Questions about firewall
Firewall: iptables, UFW, nftables, persistence, policy audit. It is categorised as a Execute tool in the Defense MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
firewall accepts 12 parameters: ipv6, port, chain, table, action, family, policy, source, dry_run, to_addr, verbose, position. Required: action. The full parameter table on this page comes from the server's own tool schema.
Register the Defense MCP server in PolicyLayer and add a rule for firewall: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Defense. Nothing to install.
firewall is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the firewall rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for firewall. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
firewall is provided by the Defense MCP server (defense-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Defense, and thousands of servers like it.
Across the catalogue