Skip to main content
Glama

privacy_vpn_connect

Connects the Proton VPN app on Windows by clicking its own connect button and reading back the real connection state, so agents can enable a VPN without guessing the result.

Instructions

Open the VPN app and ask it to connect (Proton VPN on Windows).

The agent clicks the app's OWN connect button and then reads the window, so the reported state comes from the app - 'unknown' is reported instead of a guess. It never switches servers or rotates IPs to evade a block.

Needs the vpn_control permission, which is 'deny' by default: add "vpn_control": "allow" to your permissions.json (a USER edit) to enable it.

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": "privacy_vpn_connect"
  }
}

Input Schema

NameRequiredDescriptionDefault
appNoproton

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the mechanism (agent clicks the app's own control rather than shelling out), the reporting semantics ('unknown' rather than a guessed state), the anti-evasion scope limit, and a hard authorization gate — vpn_control is deny by default and requires a user edit to permissions.json. Remaining gaps are operational: whether the call blocks until connected, any timeout, and behavior if the app is absent.

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?

Front-loaded with the action, then mechanism, then scope limit, then the prerequisite — a sensible order with no filler. The permission note is slightly verbose and the prose wraps awkwardly, but every sentence carries information.

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 low-complexity one-parameter action tool with no output schema, the definition covers purpose, side effects, honesty of reported state, and the permission gate an agent must resolve before calling. The only material omission is the value space of 'app' and expected failure modes.

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

Parameters2/5

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

Schema coverage is 0% for the single 'app' parameter, whose only hint is the default 'proton'. The parenthetical 'Proton VPN on Windows' implies proton is the supported value but never says so, and no other valid app values or what happens on an unsupported value are described. The description does not compensate for the coverage gap.

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?

States a concrete verb and resource (open the VPN app and ask it to connect) plus the platform and app (Proton VPN on Windows), and describes the mechanism (clicking the app's own connect button). This clearly separates it from the listed body_* and privacy_session_* siblings, none of which are VPN connection controls.

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?

Implies when to use it (you want the machine's VPN up) and gives an explicit exclusion: it never switches servers or rotates IPs to evade a block, so it should not be reached for circumvention. It also states the enabling prerequisite. What it lacks is a named alternative for the case where the connection fails or where a different app is needed.

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