Skip to main content
Glama
AliKarami

MikroMCP

by AliKarami
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Run Command

run_command
Destructive

Execute RouterOS console commands over SSH with an allow/deny safety policy, dry-run previews, and audit journaling; use for targeted router changes when no dedicated tool exists.

Instructions

Execute an arbitrary RouterOS console command via SSH. Guarded by an allow/deny policy (built-in deny list blocks destructive commands; tighten via cmdAllow in routers.yaml or MIKROMCP_CMD_ALLOW). Prefer dedicated tools (reboot, etc.) where available. Output capped at 4000 characters. Journaled for audit like every write (see list_journal), but never snapshotted: arbitrary commands touch unknown config sections, so it cannot be rolled back via rollback_change — prefer a dedicated tool when one exists, and note the manual undo command in your own records.

Input Schema

NameRequiredDescriptionDefault
dryRunNoPreview the command without executing (validates allow/deny policy only)
commandYesRouterOS console command to execute
routerIdNoRouter ID; omit to use the default router.
confirmationTokenNoToken from a prior APPROVAL_REQUIRED response. Re-submit the identical call with this token to confirm the destructive action.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.6.0
    • changedInput schema / properties / routerId / description
      Previous value: -"Target router identifier from the router registry"New value: +"Router ID; omit to use the default router."
    • changedInput schema / required
      Previous value: -[
-  "routerId",
-  "command"
-]New value: +[
+  "command"
+]
  2. Addedv1.5.0
  3. Removedv1.1.0
  4. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the destructiveHint annotation, the description adds substantial behavioral context: allow/deny policy enforcement, cmdAllow/MIKROMCP_CMD_ALLOW tightening, 4000-character output cap, journaling, no snapshot, and no rollback support. These details directly shape how an agent should treat the tool.

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

Conciseness5/5

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

The description is front-loaded with the core action, then layers policy, preferred alternatives, output limits, and rollback implications in a compact form. Every sentence carries operational value for a dangerous general-purpose tool.

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 high-risk arbitrary-command tool with no output schema, the description covers the essential safety, audit, output, and rollback context. It is complete enough for an agent to invoke it correctly and cautiously.

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%, so command, dryRun, routerId, and confirmationToken are already documented in the schema. The description does not add parameter-specific syntax or semantics beyond what the schema provides, so the baseline of 3 is appropriate.

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?

The description states a specific verb and resource: execute an arbitrary RouterOS console command via SSH. It also distinguishes this general escape hatch from dedicated tools such as reboot, so an agent can tell when this tool is the right one.

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

Usage Guidelines5/5

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

It gives explicit guidance: prefer dedicated tools where available, and use this only when no dedicated tool exists. It also explains that commands are journaled but never snapshotted, so rollback_change cannot undo them, which is a critical usage constraint.

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