Skip to main content
Glama
jacedomotz

Domotz MCP Server

by jacedomotz

domotz_monitoring

Manage SNMP and TCP sensors on Domotz devices: list, create, delete sensors, view history, and configure triggers with alerts.

Instructions

Manage SNMP and TCP sensors (called "Eyes" in Domotz) on devices. Use the "action" parameter to select an operation. Requires agent_id and device_id for all actions.

ACTION REFERENCE:

  • list_snmp: List all SNMP sensors on a device

  • create_snmp: Create an SNMP sensor (needs body with OID config)

  • delete_snmp: Delete an SNMP sensor (needs sensor_id)

  • snmp_history: SNMP sensor value history over time (needs sensor_id, filterable by from/to)

  • snmp_trigger_functions: List available trigger functions for an SNMP sensor (needs sensor_id) — call this FIRST to get valid function_id values

  • list_snmp_triggers: List triggers configured on an SNMP sensor (needs sensor_id)

  • create_snmp_trigger: Create a trigger on an SNMP sensor (needs sensor_id + body with function_id and value)

  • delete_snmp_trigger: Delete a trigger (needs sensor_id + trigger_id)

  • create_snmp_trigger_alert: Activate alert notifications on a trigger (needs sensor_id + trigger_id + medium_name e.g. "email", "slack")

  • delete_snmp_trigger_alert: Remove alert notifications from a trigger (needs sensor_id + trigger_id + medium_name)

  • list_tcp: List TCP sensors on a device

  • create_tcp: Create a TCP sensor (needs body with port/host config)

  • delete_tcp: Delete a TCP sensor (needs service_id)

TRIGGER WORKFLOW (must follow these steps in order):

  1. Call snmp_trigger_functions to get available function_ids (e.g. function_id=2 means "is greater than")

  2. Call create_snmp_trigger with body containing function_id and value — VERIFY the response contains the created trigger before proceeding

  3. Call create_snmp_trigger_alert with the trigger_id from step 2 to activate notifications — VERIFY the response confirms activation If ANY step returns an error, STOP and report the error to the user. Do NOT claim success without confirming each step's response.

GOTCHAS:

  • SNMP sensors and TCP sensors use different ID params: sensor_id for SNMP, service_id for TCP

  • Trigger creation requires a valid function_id from snmp_trigger_functions — do not guess function_ids

  • from/to on snmp_history accept ISO 8601 timestamps, default to last 7 days

  • TCP sensors do NOT support triggers or alerts

EXAMPLES:

  • List SNMP sensors: {"action": "list_snmp", "agent_id": 5, "device_id": 50}

  • Sensor history: {"action": "snmp_history", "agent_id": 5, "device_id": 50, "sensor_id": 3}

  • Get trigger functions: {"action": "snmp_trigger_functions", "agent_id": 5, "device_id": 50, "sensor_id": 3}

  • Create trigger (alert when value > 90): {"action": "create_snmp_trigger", "agent_id": 5, "device_id": 50, "sensor_id": 3, "body": {"function_id": 2, "value": "90"}}

  • Activate email alert on trigger: {"action": "create_snmp_trigger_alert", "agent_id": 5, "device_id": 50, "sensor_id": 3, "trigger_id": 1, "medium_name": "email"}

  • List TCP sensors: {"action": "list_tcp", "agent_id": 5, "device_id": 50}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoEnd time for time series
bodyNoRequest body (JSON object)
fromNoStart time for time series
actionYesThe operation to perform
agent_idNoAgent/Collector ID
device_idNoDevice ID
sensor_idNoSNMP Sensor ID
service_idNoTCP Service/Sensor ID
trigger_idNoTrigger ID
medium_nameNoAlert medium name (e.g. email, slack)
Behavior5/5

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

With no annotations provided, the description fully discloses behavioral traits: it specifies that sensor_id vs service_id are sensor-type-specific, trigger creation depends on valid function_id, and timeseries parameters default to last 7 days. It also warns about the exact error handling expectations ('If ANY step returns an error, STOP and report').

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 lengthy but well-structured with labeled sections (ACTION REFERENCE, TRIGGER WORKFLOW, GOTCHAS, EXAMPLES). It is front-loaded with the purpose and a key note about required parameters. While some redundancy exists (repeated requirement for agent_id and device_id in examples), the structure justifies the length given the tool's complexity.

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 high complexity (10 parameters, 13 actions, no output schema), the description covers most critical aspects: parameter usage per action, workflow order, error handling, and credential reqs. Minor gap: it does not describe return values or response structure, which a monitoring tool might rely on, but the examples and references mitigate this.

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?

Despite 100% schema description coverage, the description adds substantial meaning: it explains the 'action' enum values with context (e.g., 'list_snmp: List all SNMP sensors on a device'), clarifies parameter dependencies (e.g., 'sensor_id' needed for SNMP actions, 'service_id' for TCP), and describes the 'body' object structure (OID config, port/host, function_id, etc.) beyond the schema's generic 'Request body'.

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 'Manage SNMP and TCP sensors (called Eyes in Domotz) on devices.' This verb+resource combination precisely defines the tool's scope, distinguishing it from siblings like domotz_agents or domotz_devices which handle other aspects.

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 an ACTION REFERENCE detailing 13 specific operations with their required parameters, a TRIGGER WORKFLOW with step-by-step instructions including error handling, and GOTCHAS that clarify when not to use certain actions (e.g., TCP sensors do not support triggers). This offers explicit when-to-use and when-not-to-use guidance.

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