NetBox MCP Server

Overview Schema Source Related Servers Discussions Admin

Netbox Get Objects

netbox_get_objects

Read-onlyIdempotent

List and filter NetBox objects of any type with pagination. Returns total matches and page status, letting you query devices, IPs, or VMs by custom criteria.

Instructions

List NetBox objects of one type, with filtering and pagination.

Returns 'results' plus 'total' (all matches) and 'has_more'/'next_offset'. Results are paginated - check 'has_more' before concluding. To count objects cheaply use fields=['id'] and limit=1 and read 'total'.

Examples: netbox_get_objects('dcim.device', {'site_id': 3, 'status': 'active'}, fields=['id', 'name', 'primary_ip4']) netbox_get_objects('ipam.ipaddress', {'parent': '10.0.0.0/24'}, fields=['address', 'dns_name'])

Input Schema

TableJSON Schema

Name	Required	Description
`omit`	No	Drop these fields from the response, e.g. ['config_context', 'custom_fields']. NetBox 4.5.2+. Ignored when 'fields' is set.
`brief`	No	Return the minimal representation (id, url, display, name).
`limit`	No	Page size (1-1000).
`fields`	No	Only return these fields, e.g. ['id', 'name', 'status']. ALWAYS pass this for listings - full objects cost 10x more tokens.
`offset`	No	Number of results to skip.
`filters`	No	NetBox filters, e.g. {'site_id': 1, 'status': 'active', 'name__ic': 'core'}. Pass a list for OR: {'id': [1, 2]}. null matches empty: {'tenant_id': None}. Lookup suffixes: n, ic, nic, isw, nisw, iew, niew, ie, nie, empty, regex, iregex, lt, lte, gt, gte. NOT supported: '__in' and multi-hop lookups like 'device__site_id' - query the related object first, then filter by its ID.
`ordering`	No	Sort field(s); prefix with '-' for descending, e.g. 'name' or ['site', '-name'].
`object_type`	Yes	NetBox object type as 'app.model' (e.g. 'dcim.device', 'ipam.ipaddress', 'virtualization.virtualmachine') or as an API path ('dcim/devices'). netbox_list_object_types lists every type.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 3, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely useful behavior beyond them: the response envelope keys ('results', 'total', 'has_more', 'next_offset') and the instruction to check 'has_more' before concluding. It stops short of stating rate limits or default page size (though schema covers limit).

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 purpose and return-shape facts, then compact examples; every line earns its place. The example block is slightly verbose but directly demonstrates parameter usage, so it is defensible rather than wasteful.

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?

With an output schema present, return-value detail is not required, yet the description still explains the pagination envelope, which is the main thing an agent needs to avoid premature conclusions. For an 8-parameter, 100%-covered listing tool this is close to complete; only sibling routing is missing.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: the field-selection cost hint for counting (fields=['id'], limit=1, read 'total') and examples showing how filters and fields are passed together. That is real value beyond the structured field docs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource+scope ('List NetBox objects of one type, with filtering and pagination'), which is clearly distinct from single-object get_object and from write tools. It does not explicitly name or rule out sibling alternatives such as netbox_search_objects, so it falls short of a 5.

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

Usage Guidelines3/5

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

It gives concrete usage patterns (paginate via 'has_more', count cheaply with fields=['id'] and limit=1) and two worked examples, which is more than implied usage. However, with a sibling netbox_search_objects present, the description never says when to prefer this tool over search, nor when not to use it, so routing guidance is incomplete.

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

Deploy Server