Connect AI assistants to Domotz for network monitoring and management via MCP.
Navigate to Domotz domains (agents, devices, metrics, network, alerts, power) to access domain-specific tools.
Check Domotz API connection status and list available domains.
Manage network devices, alerts, metrics, topology, and power through the domain tools.
A Model Context Protocol (MCP) server for Domotz network monitoring and management. Enables AI assistants to monitor network devices, view alerts, check device status, and manage network infrastructure.
This is a Model Context Protocol (MCP) server that connects Claude (or any MCP-compatible AI) to your Domotz environment.
Part of the MSP Claude Plugins ecosystem — a growing suite of AI integrations for the MSP stack. Built by MSPs, for MSPs.
npm install @wyre-ai/domotz-mcpRelated MCP server: network-mcp-server
Copy .env.example and set the variables below.
Variable | Required | Description |
| For stdio and | Domotz Public API key |
| No | API region cell label (default: |
| No |
|
| No |
|
| Yes for HTTP | Service-to-service secret. The HTTP server logs an error and exits non-zero when this is empty or a known placeholder ( |
| No | Set to exactly |
| No | Bind address when |
| No | HTTP port. Defaults to |
/health stays unauthenticated and does not read credentials. The stdio transport does not use CONDUIT_S2S_SECRET.
With MCP_TRANSPORT=http and CONDUIT_S2S_SECRET set, every /mcp request must include X-Gateway-S2S. The check is verifyS2sHeader in src/s2s-verify.ts: the header value is t=<unix seconds>,v1=<hex>, where the hex is HMAC-SHA256 of the literal string t=<unix seconds> keyed with CONDUIT_S2S_SECRET (64 lowercase hex characters). The timestamp must be within 300 seconds of the server clock. A missing or invalid header returns 401 before vendor credentials are read.
TS=$(date +%s)
SIG=$(printf 't=%s' "$TS" | openssl dgst -sha256 -hmac "$CONDUIT_S2S_SECRET" -hex | awk '{print $NF}')
curl -sS http://127.0.0.1:8080/mcp \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-H "X-Gateway-S2S: t=${TS},v1=${SIG}" \
-H "X-Domotz-API-Key: $DOMOTZ_API_KEY" \
-H 'X-Domotz-Region: us-east-1' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'In AUTH_MODE=gateway, /mcp also requires X-Domotz-API-Key (X-Domotz-Region is optional and defaults to us-east-1). That header is the only credential source for the request. In AUTH_MODE=env, a valid X-Gateway-S2S header is still required and vendor credentials come from DOMOTZ_API_KEY.
Add to your Claude Desktop claude_desktop_config.json:
{
"mcpServers": {
"domotz-mcp": {
"command": "npx",
"args": ["@wyre-ai/domotz-mcp"],
"env": {
"DOMOTZ_API_KEY": "your-domotz-api-key"
}
}
}
}claude mcp add domotz-mcp \
-e DOMOTZ_API_KEY=your-value \
-- npx -y @wyre-ai/domotz-mcpThe image listens on 0.0.0.0 inside the container (MCP_HTTP_HOST) and defaults to AUTH_MODE=gateway. Publish the port on loopback and pass the S2S secret. In gateway mode, the Domotz API key arrives on each request as X-Domotz-API-Key; it is not read from the environment. Compose does not set DOMOTZ_API_KEY.
docker build -t domotz-mcp .
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-p 127.0.0.1:8080:8080 \
domotz-mcpCompose refuses to start when CONDUIT_S2S_SECRET is unset, sets AUTH_MODE=gateway, and publishes 127.0.0.1:8080:8080. Generate the secret with openssl rand -hex 32; do not use a placeholder such as your-s2s-secret.
CONDUIT_S2S_SECRET="$(openssl rand -hex 32)" docker compose upSingle-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses DOMOTZ_API_KEY:
docker run \
-e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \
-e AUTH_MODE=env \
-e DOMOTZ_API_KEY=your-value \
-e DOMOTZ_REGION=us-east-1 \
-p 127.0.0.1:8080:8080 \
domotz-mcpLocal HTTP without a secret is development-only. It binds 127.0.0.1 only and logs a warning. A non-loopback MCP_HTTP_HOST, including 0.0.0.0, is ignored:
MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm run start:httpManage Domotz monitoring agents
View and manage network alerts
Device discovery and status monitoring
Network performance metrics
Network topology and configuration
Power management for managed devices
# Clone the repository
git clone https://github.com/WYRE-AI/domotz-mcp.git
cd domotz-mcp
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
# HTTP transport refuses to start until CONDUIT_S2S_SECRET is a real secret
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" npm run start:http
# Local HTTP only, without a service-to-service secret (always binds 127.0.0.1)
MCP_ALLOW_INSECURE_DEV=1 npm run start:httpContributions are welcome! Please see CONTRIBUTING.md if present, or open an issue to discuss changes.
Licensed under the Apache License, Version 2.0. See LICENSE for details.
Check Domotz API connection status and available domains.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It indicates a read-only check operation, which is appropriate, but lacks details on backend calls, authentication, or performance implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no extraneous words. Perfectly concise for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a parameterless tool with no output schema, the description covers the essential purpose. However, it omits details about the response format or what 'available domains' means, which could be slightly improved.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so the description adds no parameter meaning. Baseline is 4 because no parameter documentation is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Check') and clearly specifies the resource ('Domotz API connection status and available domains'). It distinguishes itself from the sibling 'domotz_navigate' tool by focusing on status rather than navigation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when needing to verify connectivity or list domains, but provides no explicit guidance on when to avoid this tool or compare with siblings like 'domotz_navigate'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.4domotz_navigatedomotz_statusScored across 2 tools
The two tools have completely distinct purposes: one navigates to various domains, the other checks API status. No overlap or ambiguity.
Both tools follow the same 'domotz_verb' pattern with simple, clear verbs: 'navigate' and 'status'. Consistent and predictable.
With only 2 tools covering a wide range of domains (agents, devices, metrics, network, alerts, power), the tool surface is too thin for the apparent scope. Likely requires heavy parameterization in a single tool.
The server only provides navigation to domains and status check, but no actual CRUD or action tools for those domains. This is severely incomplete for practical management tasks.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
