Skip to main content
Glama

Read VPN log

get_logs
Read-only

Retrieve recent VPN log lines for a profile to diagnose failed connections, choosing raw VPN output or PassTunnel activity events; credentials are redacted.

Instructions

Returns the last lines of a profile's VPN log, for explaining why a connection failed. source "raw" (the default): the OpenVPN, openfortivpn or openconnect output of the current or last session. source "activity": what PassTunnel did and saw, also for sessions the app or a terminal started (connecting, waiting for a fresh code, credentials sent, sign-in accepted or rejected, connected, drops, reconnects, stopped by the user), as sentences in lines and as typed events. Anything that looks like a credential is replaced by ; passwords and one-time codes are never included.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "profile_id": "<profile_id>"
    },
    "name": "get_logs"
  }
}

Input Schema

NameRequiredDescriptionDefault
linesNoNumber of lines (or activity events) from the end of the log.
sourceNoraw: the VPN tool's output; activity: PassTunnel's own record of the connection.raw
profile_idYesA profile id from list_profiles.

Output Schema

NameRequiredDescriptionDefault
idYes
linesYes
eventsNo
sourceNo
truncatedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds genuinely new behavior: credential-like strings become <redacted> and passwords/one-time codes are never included, plus the fact that 'raw' may reflect the current or a previous session. It does not state what happens when no log exists yet or whether output is truncated at the 500-line cap.

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 purpose in the first clause, then the source variants, then the redaction guarantee – a sensible priority order with no filler. The long parenthetical event list is dense and the phrase 'as sentences in lines and as typed events' is slightly awkward, but the content earns its space.

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 simple read tool with an output schema and full annotation coverage, this covers what an agent needs: both source modes, the session scope, and the redaction guarantee. The only real gap is the absence of guidance relative to the neighboring 'diagnose' tool, which addresses the same failure-explanation scenario.

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

Parameters4/5

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

Schema coverage is 100%, so baseline would be 3, but the description goes further than the schema's one-line enum hints by naming the concrete producers behind 'raw' (OpenVPN, openfortivpn, openconnect) and enumerating the kinds of events 'activity' records. This materially helps an agent choose a source value rather than guess.

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?

A specific verb and resource ('Returns the last lines of a profile's VPN log') plus the intent ('for explaining why a connection failed') make the purpose unambiguous. It never names the overlapping sibling 'diagnose', so an agent must infer on its own which of the two to reach for when troubleshooting a failed connection.

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?

The description clearly frames the use case (diagnosing a connection failure) and, crucially, explains which source to pick for which situation – 'raw' for the VPN tool's own output versus 'activity' for what PassTunnel did, including sessions started outside the app. It stops short of explicit exclusions, e.g. it does not say to prefer 'diagnose' for a summarized verdict or 'get_status' for current state.

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