Skip to main content
Glama

Get connection status

get_status
Read-only

Check VPN connection state for every profile or one profile: disconnected, connecting or connected, tunnel IP, last error and cause, retry timing, and whether the privileged helper is installed.

Instructions

Returns the connection state of every profile (or only profile_id): disconnected, connecting or connected, the tunnel IP, since when, the last error and why it happened (failure: auth_rejected, host_not_found, unreachable, configuration, setup, timeout, cancelled, tool_unsupported (the VPN tool does not run on this macOS version), host_scan_required (a Cisco AnyConnect server requires a host scan, which PassTunnel never runs), sso_required (a Palo Alto GlobalProtect portal or gateway signs in with single sign-on, which PassTunnel does not support) or failed; for a configuration failure, server_cert (the key of the server whose certificate was not trusted) and, for GlobalProtect, gateways (the portal's gateways when the profile's gateway names none of them); the server's reply; whether the sign-in and a one-time code were sent; for a rejected sign-in, clock: how far this computer's clock was off, when known), when the app tries a server that did not answer again (next_try_at, tries), and whether the privileged helper that starts VPNs is installed and current. connect_refusal says why a profile cannot be connected on this system at all. experimental is true on a profile of an experimental type (Palo Alto GlobalProtect); notices lists what the user should know about a connected profile (hip_report_not_sent).

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": "get_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
profile_idNoA profile id from list_profiles; omit for all profiles.

Output Schema

NameRequiredDescriptionDefault
helperYes
profilesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine domain semantics (what each failure code means, e.g. tool_unsupported or sso_required), but it covers almost nothing about behavior beyond the returned data — no mention of cost, freshness, or side effects. It is rich but oriented entirely toward return content rather than tool behavior.

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

Conciseness2/5

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

The body is a single sprawling sentence with multiple levels of nested parentheses, making it hard to parse. Much of that bulk enumerates return fields (tunnel IP, next_try_at, notices, experimental) that the existing output schema already documents, so it does not earn its length. The one virtue is that the core purpose is front-loaded.

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 one-optional-parameter read-only tool with an output schema, the definition is more than complete — it exhaustively explains error codes and profile flags. The only real gap is guidance on when to prefer this over diagnose/get_logs, which is modest for such a simple tool.

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% and the schema already states 'omit for all profiles', so the description's '(or only profile_id)' adds nothing new. Baseline 3 applies.

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?

The opening clause states a specific verb and resource ('Returns the connection state of every profile') and scopes it with the optional profile_id. It is clearly a status-reading tool, though it never contrasts itself with siblings like diagnose or get_logs.

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

Usage Guidelines3/5

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

Usage is only implied through '(or only profile_id)' and the note that connect_refusal explains why a profile cannot be connected. There is no explicit when-to-use versus diagnose or get_logs, and no stated precondition or follow-up action.

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