Skip to main content
Glama
jacedomotz

Domotz MCP Server

by jacedomotz

domotz_agents

Manage Domotz collectors: list, delete, monitor activity, bandwidth, VPNs, uptime, speed tests, IP conflicts, and more.

Instructions

Manage Domotz collectors (agents). Use the "action" parameter to select an operation. Requires agent_id for most actions.

ACTION REFERENCE:

  • list: List all collectors (paginated, filterable by display_name/team_name)

  • count: Count collectors (lightweight HEAD request, returns {"count": N})

  • get: Get single collector details by agent_id

  • delete: Delete a collector

  • activity_log: Collector activity log (filterable by from/to/type)

  • connection_consumption: Bandwidth consumption data

  • vpn_connections: List VPN sessions

  • create_vpn: Create a VPN session (needs body)

  • delete_vpn: Delete a VPN session (needs vpn_session_id)

  • status_history: Online/offline event history (filterable by from/to)

  • speed_test_history: Internet speed test results (filterable by from/to)

  • ip_conflicts: Detected IP conflicts on a collector

  • rtd_stats: Round-trip delay statistics for all devices on a collector

  • network_topology: Network topology map

  • uptime: Collector uptime percentage (filterable by from/to)

  • list_uptime_all: Uptime for ALL collectors (no agent_id needed - the only action that doesn't require one)

  • variables: Collector-level variables (paginated, filterable by value/path/metric)

  • count_variables: Count collector variables (lightweight HEAD request)

  • variable_history: Time-series for a specific variable (needs variable_id)

  • move: Move collector to a different team (needs team_id)

  • eyes_usage: SNMP/TCP sensor usage statistics

  • metric_usage: Metric usage statistics

  • device_applications: Applications across all devices on collector (paginated)

  • count_device_applications: Count applications (lightweight HEAD)

  • device_variables: Variables across all devices on collector (paginated)

  • count_device_variables: Count device variables (lightweight HEAD)

  • eyes_snmp: All SNMP sensors across collector

  • eyes_tcp: All TCP sensors across collector

  • unmanaged_devices: Devices not being monitored

  • external_host: Add an external host to monitor (needs body)

  • dhcp_discovery: Configure DHCP discovery (needs body)

GOTCHAS:

  • count/count_variables/count_device_applications/count_device_variables use HEAD requests and return {"count": N} from the X-Entities-Count header

  • list_uptime_all is the ONLY action that works without specifying agent_id

  • from/to accept ISO 8601 timestamps, default to last 7 days if omitted

  • Use page_size (1-1000) and page_number (0-based) for large result sets

EXAMPLES:

  • List all collectors: {"action": "list"}

  • Get collector details: {"action": "get", "agent_id": 5}

  • Check for IP conflicts: {"action": "ip_conflicts", "agent_id": 12}

  • Show network topology: {"action": "network_topology", "agent_id": 8}

  • Uptime for all collectors: {"action": "list_uptime_all"}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoEnd time for time series (default: now)
bodyNoRequest body (JSON object)
fromNoStart time for time series (default: one week ago)
nameNoFilter applications by name
pathNoFilter variables by path
typeNoActivity log type filter
valueNoFilter variables by value
actionYesThe operation to perform
metricNoFilter by metric
sort_byNoSort field for variables
team_idNoTeam ID (for move action)
agent_idNoAgent/Collector ID
page_sizeNoMax items to return (1-1000)
team_nameNoFilter by team name
device_idsNoFilter applications by device IDs
has_historyNoFilter by has_history field
page_numberNoPage number, 0-indexed
variable_idNoVariable ID
display_nameNoFilter by display name (case insensitive)
vpn_session_idNoVPN Session ID
sorting_directionNoSort direction (asc/desc)
Behavior4/5

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

As no annotations are present, the description fully covers behavioral traits: lightweight HEAD requests for count actions, the exception for list_uptime_all, pagination details, ISO 8601 defaults, and required parameters. It could add more on side effects of destructive actions like delete.

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 long but well-structured with clear sections (ACTION REFERENCE, GOTCHAS, EXAMPLES) and front-loaded purpose. Every part serves a purpose, though some redundancy exists.

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 tool's complexity (21 parameters, 31 actions) and lack of output schema, the description is thorough. It covers actions, parameters, and edge cases, but lacks return value details for many actions and examples for body parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the description goes far beyond by grouping parameters by action, explaining when they apply, providing gotchas and examples. This adds significant value for correct invocation.

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 resource ('Domotz collectors (agents)') and the purpose ('Manage'), and provides a comprehensive list of specific actions. It is distinct from sibling tools focused on other resource types.

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 explains when to use each action (e.g., which require agent_id, which are lightweight HEAD requests) and provides filtering/pagination guidance. It does not explicitly contrast with sibling tools but the domain is clear.

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/jacedomotz/domotz-mcp-server'

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