Skip to main content
Glama

vpn_client

Destructive

Configure outbound VPN profiles, select the active one, and add or remove devices so chosen clients route through a filtering VPN.

Instructions

The router's VPN CLIENT (router dials out). Configure a VPN, then choose which devices use it - this is how e.g. a child's device can be sent through a filtering VPN. Profiles: action=profiles | add_profile (profile={key,...}; added disabled) | set_active_profile (key; the ENABLED profile is the one in use) | update_profile / remove_profile (key). Devices (they use WHICHEVER profile is active; there is no per-device profile): devices | candidates | add_device (mac, name?, client_type?) | set_device (mac, use_vpn=true|false) | remove_device (mac). Also status | connection_status (key) | enable | disable. Everything that changes profiles or devices is CRITICAL.

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": "vpn_client"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNo
macNo
nameNo
applyNofalse (default) = dry run: show the plan, diff, warnings and risk, send nothing. true = send it.
actionNostatus
revealNoShow secrets (passwords/keys) unmasked.
routerNoWhich router (see router_status 'routers'); default main.main
profileNo
use_vpnNo
client_typeNo
confirm_tokenNoRequired with apply=true for CRITICAL changes: the token from the dry run (valid 5 minutes, bound to the exact plan and current router state).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructive=true and readOnly=false, and the description stays consistent while adding real behavioral facts: add_profile creates profiles disabled, the ENABLED profile is the one in use, there is no per-device profile binding, and everything mutating profiles/devices is CRITICAL (tying to the confirm_token flow). It does not discuss permissions/auth scope or whether removed profiles affect in-flight connections.

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

Conciseness4/5

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

Purpose is front-loaded and the pipe-delimited action list is dense but scannable, with no filler sentences. The telegraphic style ("(they use WHICHEVER profile is active; there is no per-device profile)") trades some readability for compactness in a 14-action tool.

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 a multiplexed tool with 14 actions, 11 parameters, nested objects and no output schema, the description is unusually complete: it enumerates every action, ties parameters to actions, and flags which operations are CRITICAL. Gaps remain on what status/connection_status/profiles return and what `candidates` signifies, which matters more given there is no output schema.

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 only 36%, but the description maps most action-specific parameters to their actions (key for set_active_profile/connection_status, mac/name/client_type for add_device, mac/use_vpn for set_device, profile object for add_profile), which compensates materially. The shared control parameters (apply, confirm_token, reveal, router) are covered by the schema rather than the description, so this sits at the baseline rather than above it.

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

Purpose5/5

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

The opening line states a specific verb and resource and disambiguates from the sibling: "The router's VPN CLIENT (router dials out)", which immediately separates it from vpn_server. The description then enumerates the full action surface (profiles, devices, status, enable/disable), so an agent knows the tool's complete scope without opening the schema.

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?

It gives an explicit operating model — "Configure a VPN, then choose which devices use it" — plus a concrete use case (routing a child's device through a filtering VPN) and the key constraint that devices use whichever profile is active. It lacks explicit when-not-to-use guidance (e.g. when to prefer vpn_server or parental_control instead).

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