Skip to main content
Glama

List Devices

netbox_list_devices
Read-onlyIdempotent

List physical devices from NetBox with pagination, fuzzy text search, and filters by name, site, status, serial, and more.

Instructions

List physical devices (switches, routers, servers, firewalls, etc.) from NetBox.

Supports pagination and filtering. Common patterns:

  • Discovery: call with no filters to browse the first devices.

  • Lookup by id: use netbox_get_device instead when you already have an id.

  • Narrow scan: combine 'q' (fuzzy text) with resource-specific filters below.

Pagination:

  • 'limit' (max 1000, default 50) and 'offset'. Response includes 'has_more' and 'next_offset'.

  • Large list responses auto-truncate to keep under the character limit; keep calling with next_offset to continue.

Resource-specific filters:

  • name: Exact device name (case-insensitive).

  • name__ic: Device name contains (case-insensitive).

  • serial: Exact serial number.

  • asset_tag: Exact asset tag.

  • site_id:

  • location_id:

  • rack_id:

  • role_id:

  • manufacturer_id:

  • device_type_id:

  • platform_id:

  • tenant_id:

  • status:

  • mac_address: Filter by any interface MAC (lowercase colon form).

  • has_primary_ip:

Universal filters:

  • q (string) Fuzzy text search across searchable fields.

  • tag (string[]) AND-filter by tag slugs.

  • created_after (date) ISO-8601 lower bound on 'created'.

  • created_before (date) ISO-8601 upper bound on 'created'.

Returns: Markdown summary (default) or JSON with shape: { total, count, offset, limit, items: [...], has_more, next_offset? }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFuzzy full-text search across the object's searchable fields (name, description, etc.).
tagNoFilter to objects that have ALL of these tag slugs. Repeat for multiple tags (AND semantics in NetBox).
nameNoExact device name (case-insensitive).
limitNoMaximum number of items to return per page (1-1000, default 50).
offsetNoNumber of items to skip for pagination. Use next_offset from a previous response.
serialNoExact serial number.
statusNo
rack_idNo
role_idNo
site_idNo
name__icNoDevice name contains (case-insensitive).
asset_tagNoExact asset tag.
tenant_idNo
location_idNo
mac_addressNoFilter by any interface MAC (lowercase colon form).
platform_idNo
created_afterNoISO-8601 date; only return objects created on or after this date (e.g. 2024-01-01).
created_beforeNoISO-8601 date; only return objects created on or before this date.
device_type_idNo
has_primary_ipNo
manufacturer_idNo
response_formatNoOutput format: 'markdown' (default, human-readable) or 'json' (full structured payload). Use 'json' when chaining follow-up tool calls.markdown
Behavior4/5

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

Annotations already declare read-only, open-world, idempotent, and non-destructive hints. The description adds value by detailing pagination mechanics, auto-truncation, and response shape (has_more, next_offset). It does not contradict annotations.

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-organized into sections (common patterns, pagination, resource-specific filters, universal filters, returns), and the primary purpose is stated first. It is somewhat lengthy but justified by the large parameter count. A minor point: some filter descriptions repeat schema info.

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

Completeness4/5

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

Given the complexity (22 parameters, no output schema), the description covers pagination, auto-truncation, and response format. It mentions the main sibling tool for retrieval. It does not explain how to chain with other list tools, but that is acceptable for a focused list tool.

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 coverage is 55% (12 of 22 parameters have descriptions). The description adds grouping (resource-specific vs universal filters) and clarifies several filters (e.g., mac_address, has_primary_ip, created_after/before). However, it omits descriptions for site_id, location_id, rack_id, role_id, manufacturer_id, device_type_id, platform_id, tenant_id, and status (despite having an enum). Thus it adds partial but incomplete value.

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 clearly states the tool lists physical devices from NetBox and distinguishes itself from netbox_get_device by specifying when to use each (e.g., 'use netbox_get_device instead when you already have an id'). It also lists the types of devices, making the purpose 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?

The description provides explicit usage patterns: discovery with no filters, lookup by id using a sibling tool, and narrow scans combining fuzzy search with filters. It also explains pagination handling (limit, offset, has_more, next_offset) and auto-truncation behavior.

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/ZenixSolutions/netbox-mcp-server'

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