Skip to main content
Glama
rstierli

FortiManager MCP Server

by rstierli

install_package

Deploy firewall policies and configurations by installing a policy package to managed devices. Preview changes before applying to verify without commitment.

Instructions

Install a policy package to managed devices.

Deploys firewall policies and configurations from a policy package to the specified devices. This is an asynchronous operation - use wait_for_task() to monitor completion.

By default (FMG_INSTALL_SAFETY=strict) a real install requires a verified preview first: run preview_install for the same ADOM, package, and devices, wait for its task to finish, then install. Each preview authorizes one install, and only while the package is unchanged — if the package was edited after the preview, the install is refused (preview_stale) and a fresh preview is required.

Args: adom: ADOM name package: Policy package name devices: Target devices [{"name": "FGT1", "vdom": "root"}, ...] preview: If True, only preview changes without applying (default: False)

Returns: dict: Installation result with keys: - status: "success" or "error" - task_id: Task ID for monitoring (if successful) - message: Status or error message

Example: >>> # Install to single device >>> result = await install_package( ... adom="root", ... package="default", ... devices=[{"name": "FGT-HQ", "vdom": "root"}] ... ) >>> if result["status"] == "success": ... await wait_for_task(result["task_id"])

>>> # Preview installation first
>>> result = await install_package(
...     adom="root",
...     package="default",
...     devices=[{"name": "FGT-HQ", "vdom": "root"}],
...     preview=True
... )

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
adomYes
packageYes
devicesYes
previewNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

Without annotations, the description carries full responsibility for behavioral disclosure. It clearly states that the operation is asynchronous, requires a preview before actual install, and that preview authorizes a single install only when the package is unchanged. It also explains the preview parameter behavior and what the return value contains (status, task_id, message).

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 well-structured with a summary line, a behavioral paragraph, parameter list, return values, and examples. It is slightly verbose but every part adds value. The examples are helpful. Could be slightly more concise, but still effective.

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?

The description covers all necessary aspects: purpose, usage workflow, parameters, return values, and examples. With an output schema present, the description still provides sufficient context about return values. It is complete for an agent to correctly select and invoke the tool.

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?

With 0% schema description coverage, the description compensates by explaining each parameter: adom, package, devices (with example format), and preview (default False, preview-only behavior). The device parameter format is shown in the example and args section, adding meaning beyond the schema types.

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 explicitly states the tool's purpose: 'Install a policy package to managed devices.' It specifies the action (install) and the resource (policy package), and distinguishes it from sibling tools like preview_install and assign_* tools by focusing on deployment of firewall policies from a package to devices.

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 provides clear guidance on when to use the tool, including the prerequisite of a verified preview via preview_install and the behavior of the preview parameter. It also explains the asynchronous nature and need to use wait_for_task. However, it does not explicitly mention alternatives or when not to use it, such as for assigning templates.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rstierli/fortimanager-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server