Skip to main content
Glama

add_tunnel

Save local, remote, or SOCKS5 SSH tunnels through a vault host, routing ports without exposing credentials, and optionally start them immediately.

Instructions

Save a tunnel through a host (needs vault:edit; for a team's host, one your access reaches): local (ssh -L), remote (ssh -R) or dynamic (SOCKS5, ssh -D).

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": {
      "name": "<name>",
      "kind": "<kind>",
      "via": "<via>"
    },
    "name": "add_tunnel"
  }
}

Input Schema

NameRequiredDescriptionDefault
viaYesThe host it goes through: a host of the person's vault, by name.
kindYes
nameYes
portNoThe port it listens on: on this computer (local, dynamic) or on the host (remote). For local, default: the target's port.
startNoStart it right away (needs the tunnels scope on the host). Default false.
targetNohost:port it leads to (local, remote). Not for dynamic.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations provided, the description carries the full behavioral burden. It usefully discloses the vault:edit permission requirement and the team-host access condition, but it does not describe what happens on duplicate names, whether saving overwrites an existing tunnel, or whether the operation is purely persistent configuration versus immediate activation.

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?

The description is a single compact sentence with the core action front-loaded and the three kinds clearly enumerated. The parenthetical nesting is dense but still readable and does not waste words.

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

Completeness3/5

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

For a six-parameter mutation tool with no output schema and no annotations, the description covers permissions and tunnel kinds but leaves gaps around name uniqueness, save-versus-start behavior, and failure modes. It is adequate but not fully complete for an agent to call this confidently without inspecting the 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 67%, so several parameters are already documented in the schema. The description reinforces kind semantics but adds little beyond the schema for name, port defaults, or target applicability. Baseline 3 is appropriate given the partial schema coverage.

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 description uses a specific verb and resource: 'Save a tunnel through a host.' It also distinguishes the three tunnel kinds (local, remote, dynamic) with their ssh equivalents, which helps an agent understand exactly what is being created. It stops short of explicitly contrasting this with sibling operations like start_tunnel or update_tunnel.

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?

The definition gives a prerequisite ('needs vault:edit') and a scoping condition for team hosts, which helps decide whether the call can succeed. However, it does not explicitly say when to use add_tunnel versus start_tunnel or update_tunnel, leaving the workflow relationship implied rather than stated.

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