Skip to main content
Glama
cacack

vyos-mcp

by cacack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

vyos_configure

Applies batched VyOS set/delete configuration changes atomically with commit-confirm, auto-reverting unless confirmed within five minutes.

Instructions

Apply a list of VyOS config changes atomically with commit-confirm.

Every operation in `commands` is applied in a single commit-confirm
window — the whole batch commits or rolls back together, never
partially. Prefer batching all related set/delete changes into one
call rather than making several sequential calls; this is faster and
keeps related changes atomic.

This is the safe default — changes auto-revert after 5 minutes unless
confirmed with vyos_confirm. Confirm or let a pending window expire
before calling again: a call while one is pending commits WITHOUT its
own rollback and raises. An error saying changes were COMMITTED means
they are live; do not retry blindly. A `warning` key in the result
means auto-rollback could not be verified (`service https` changes).

Args:
    commands: List of config operations, each with 'op'
        ('set'/'delete') and 'path' (list of strings). Pass as many
        as belong together. Example:
        [{"op": "set", "path": ["firewall", "group",
          "network-group", "MY_GROUP", "network", "10.0.0.0/8"]},
         {"op": "set", "path": ["firewall", "group",
          "network-group", "MY_GROUP", "network", "192.168.0.0/16"]}]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
commandsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: atomic commit-or-rollback, auto-revert after 5 minutes, behavior when a window is already pending (commits without rollback and raises), the meaning of a COMMITTED error, and the `warning` key for unverified rollback. These are exactly the operational traits an agent needs.

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 core semantics, then batching advice, then safety/caveats; every paragraph carries actionable content. It is somewhat long and the inline example is verbose, but nothing is redundant.

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

Completeness5/5

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

For a mutation tool with no annotations and no output schema, the description covers prerequisites, rollback timing, failure semantics, and result keys (warning/COMMITTED). Nothing an agent needs to invoke it safely is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate, and it does: it defines each command as an object with 'op' ('set'/'delete') and 'path' (list of strings), and provides a concrete worked example. This fully documents the otherwise opaque array-of-objects parameter.

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 specific verb (apply) and resource (VyOS config changes), and the atomic commit-confirm scope distinguishes it from plain mutation siblings. The agent can tell it applies a batch atomically rather than incrementally.

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?

Gives clear batching guidance ('prefer batching... into one call') and names vyos_confirm as the follow-up, plus a prerequisite about pending windows. It does not, however, distinguish when to use this over the closely related vyos_merge/vyos_load siblings, leaving that inference to the agent.

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