Skip to main content
Glama
FortiManager MCP Server

FortiManager MCP Server

by rstierli

get_device_sdwan_monitor

Read a device's live SD-WAN runtime status through FortiManager to see per-member link health, bandwidth, and SLA metrics. Use it to check uplink performance and find members breaching SLA targets.

Instructions

Read a device's LIVE SD-WAN Monitor status through the FortiManager proxy.

Unlike get_device_sdwan (which reads the device-DB SD-WAN config), this proxies the device's live monitor API to return current SD-WAN runtime state -- the data the FortiManager "SD-WAN Monitor" view shows:

  • per-member link status and up/down bandwidth (virtual-wan/members)

  • per-member SLA health for each health-check: latency, jitter, packet loss and which SLA targets are met (virtual-wan/health-check)

Use it to answer "how are the uplinks doing right now / which member is breaching SLA", which the config read cannot answer.

Args: adom: ADOM name (defaults to DEFAULT_ADOM / "root" when omitted) device: Managed device name (e.g. "FGT-HQ"). Defaults to DEFAULT_DEVICE when omitted; required if that is not configured.

Returns: dict with keys: - adom, device - members: raw virtual-wan/members proxy response (None if it failed) - health_check: raw virtual-wan/health-check proxy response (None if it failed) - summary: condensed member links/bandwidth + per-member SLA - unverified: reads that failed while the other one worked; a failed read adds nothing to the summary - error / error_code: on failure, or when both reads failed

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": "get_device_sdwan_monitor"
  }
}

Input Schema

NameRequiredDescriptionDefault
adomNo
deviceNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.12.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations the description must carry the burden, and it largely does: it discloses partial-failure semantics (members/health_check return None on individual failure, 'unverified' captures partial reads, error/error_code set when both fail) and default resolution for adom/device. It stops short of stating permissions/auth needs or that the data is a point-in-time snapshot rather than a stream, which for a live-monitor tool would be worth one more line.

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 distinction before any detail, and the Args/Returns structure is easy to scan. Some redundancy remains — the Returns section restates information already carried by the output schema — and the doubled-backtick markup adds noise without adding meaning.

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 two-parameter read with no annotations, the description covers purpose, the sibling distinction, defaulting behavior, response shape, and partial-failure handling — everything needed to call it correctly and interpret an ambiguous result. The output schema exists, so the Returns block is a bonus rather than a gap-filler.

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 description coverage is 0%, so the description must compensate — and it does, documenting both parameters with their fallback defaults (DEFAULT_ADOM / 'root', DEFAULT_DEVICE) and the conditional requirement that device is required when no default is configured. It doesn't add format hints beyond the 'FGT-HQ' example, so it is strong but not exhaustive.

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 and resource — reading LIVE SD-WAN Monitor runtime state through the FortiManager proxy — and immediately contrasts it with the sibling get_device_sdwan (config vs. runtime). The two bullet points naming virtual-wan/members and virtual-wan/health-check make the scope of the read unambiguous.

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?

Explicitly routes the agent: use this for 'how are the uplinks doing right now / which member is breaching SLA', and explicitly says the config read cannot answer that. The alternative (get_device_sdwan) is named with the condition that selects it, which is exactly what guidance should do.

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