Skip to main content
Glama

Read the firewall log

proxmox_get_firewall_log
Read-only

Read node or guest firewall logs to inspect logged traffic and identify packets matching rules with logging enabled; filter by scope, time range, search terms, and result limits.

Instructions

Read the firewall log of a node (all its traffic, including guests on it) or of one guest. Only packets matching rules/policies with a log level other than nolog are logged; set log_level_in on the options or log on a rule to see drops.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "proxmox_get_firewall_log"
  }
}

Input Schema

NameRequiredDescriptionDefault
nodeNoNode name: the host for scope node (defaults to PROXMOX_DEFAULT_NODE or the only node), or the guest's node for scope guest (looked up from vmid when omitted)
vmidNoVM or container ID, for scope guest
limitNoMaximum number of results (default 100)
scopeNoFirewall level: node = a host's own firewall; guest = a VM or container (give vmid). Inferred when omitted: guest if vmid is given, node if node is given, otherwise node.
sinceNoOnly entries since this UNIX time
startNoSkip this many lines (paging)
untilNoOnly entries until this UNIX time
searchNoCase-insensitive substring filter on names, IDs, tags and similar fields

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds a genuinely useful behavioral caveat beyond the annotations: results are filtered by log-level configuration, so absence of entries does not mean absence of traffic. It still says nothing about ordering, retention, or return shape, which keeps it at 3 rather than higher.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with what the tool reads and for which scope, followed by the log-level precondition and the remedy. No filler and nothing an agent must re-read.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, zero-required read tool with no output schema, this covers purpose, scope, the main caveat, and the fix for missing entries. Paging and time-window behavior are left entirely to the schema, which is acceptable, but return ordering and default limit are unmentioned here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so node, vmid, limit, start, since, until, search and the scope enum are all documented in the schema itself, including scope inference rules. The description adds only the node-scope-includes-guests point; the mention of log_level_in and `log` refers to the firewall options/rule tools rather than this tool's parameters, so it does not deepen this schema's semantics. Baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Read the firewall log") and pins the two scopes precisely: a node's log, which includes traffic from guests on it, or a single guest's log. That scope distinction is clear without opening the schema. It does not name or contrast any sibling log tool (ceph/cluster/task), so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives real operational context: only packets matching rules or policies with a log level other than nolog appear, and it points to setting log_level_in on the options or `log` on a rule to surface drops. That pre-empts the most likely confusion (an apparently empty log). It offers no explicit when-to-use versus alternatives, so not a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools