GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Descripción del creador (original en inglés)
Control Homebridge accessories and scenes, manage plugins and config.json, and read logs
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
HOMEBRIDGE_URL, HOMEBRIDGE_TOKEN, HOMEBRIDGE_USERNAME, HOMEBRIDGE_PASSWORD, HOMEBRIDGE_READ_ONLYLos valores marcados como secretos son llaves de tu cuenta. Nunca los compartas ni los pegues en un chat.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Descargar el archivo .mcpb del creador
El enlace lleva al archivo del propio creador; no lo alojamos ni lo reempaquetamos. Abre el archivo y Claude Desktop lo instalará.
Ejecuta esto en tu terminal
claude mcp add homebridge-ai-kit --env HOMEBRIDGE_URL=your-value --env HOMEBRIDGE_TOKEN=your-value --env HOMEBRIDGE_USERNAME=your-value --env HOMEBRIDGE_PASSWORD=your-value --env HOMEBRIDGE_READ_ONLY=your-value -- npx -y @mp-consulting/homebridge-ai-kit mcpCompleta los valores vacíos antes de ejecutarlo.
Pégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"homebridge-ai-kit": {
"command": "npx",
"args": [
"-y",
"@mp-consulting/homebridge-ai-kit",
"mcp"
],
"env": {
"HOMEBRIDGE_URL": "your-value",
"HOMEBRIDGE_TOKEN": "your-value",
"HOMEBRIDGE_USERNAME": "your-value",
"HOMEBRIDGE_PASSWORD": "your-value",
"HOMEBRIDGE_READ_ONLY": "your-value"
}
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"homebridge-ai-kit": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mp-consulting/homebridge-ai-kit",
"mcp"
],
"env": {
"HOMEBRIDGE_URL": "your-value",
"HOMEBRIDGE_TOKEN": "your-value",
"HOMEBRIDGE_USERNAME": "your-value",
"HOMEBRIDGE_PASSWORD": "your-value",
"HOMEBRIDGE_READ_ONLY": "your-value"
}
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Este se ejecuta en tu computadora, y ChatGPT solo puede conectarse a servidores en internet. Elige otra app.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
HOMEBRIDGE_USERNAME envHOMEBRIDGE_READ_ONLY envEsta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Se ejecuta en tu computadora; la lista de herramientas aparece en tu app de IA después de instalarlo.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 8 nov 2026
El nombre en el registro se verificó con la cuenta de GitHub mp-consulting, dueña del repo
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Este se ejecuta en tu computadora; no hay endpoint en internet
Se ejecuta en tu computadora y usa ajustes locales en su lugar
Se ejecuta en tu computadora; solo podemos leer listas de herramientas de endpoints en internet
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 1 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
Debes completar: HOMEBRIDGE_URL, HOMEBRIDGE_TOKEN, HOMEBRIDGE_PASSWORD
Se ejecuta en tu computadora. Tu app de IA lo inicia cuando hace falta, y los datos no pasan por los servidores del creador (a menos que el propio servidor llame a un servicio en línea).
El repo de GitHub cambió por última vez –, y la última versión (3.1.3) llegó al registro hace 17 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. También necesitas Node.js, MCPB en tu computadora.
En la misma categoría: GitHub, Desktop Commander, Cloudflare MCP
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:↓ Descargas por semanai★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
AI toolkit for Homebridge, in one package:
HomebridgeAiKit platform) with a settings page to pick the provider and model, test the connection, serve MCP over HTTP and generate client configs.The AI building blocks that don't need MCP also ship on their own as @mp-consulting/homebridge-ai-core — see Packages.
Renamed from `@mp-consulting/homebridge-mcp-server`. The old
homebridge-mcp-servercommand still works, so existing MCP client configs don't need to change. See Migrating from homebridge-mcp-server.
This repository is an npm workspace that publishes two packages, both at version 2.0.0:
| Package | Use it for | Runtime dependencies |
|---|---|---|
@mp-consulting/homebridge-ai-core | Homebridge plugins. The plugin-UI Assistant routes (registerAiRoutes from ./plugin), providers, redaction, prompts, config and the Assistant features (everything except runAgent). | ajv only |
@mp-consulting/homebridge-ai-kit (this package) | Homebridge Glass UI and MCP. Everything in ai-core (re-exported) plus the MCP server, runAgent, the HomebridgeAiKit Homebridge plugin and mcpClientSnippets. | ai-core, @modelcontextprotocol/sdk, socket.io-client, zod, undici, @homebridge/plugin-ui-utils |
Plugins should depend on ai-core, so installing them doesn't pull in the MCP SDK, socket.io or zod. ai-kit stays backward compatible: its . and ./plugin exports re-export everything ai-core has under the same names, so code that imports from ai-kit keeps working.
MCP tools (43): accessories (list, get, control with value checks, bulk control with dryRun, locks / garage doors / alarms behind confirmation, room layout, sensor history), scenes (list, run, save), server (status, restart, pairing, cached accessories), child bridges (list, health, restart, stop, start), config (read with secrets redacted, full write, partial patch_config, dryRun diffs, backups and restore), instance backups, test notifications, plugins (list, search, versions, schema, changelog, install, update, uninstall), system info and logs (recent lines, filtered regex search).
MCP resources you can subscribe to: homebridge://accessories, homebridge://logs/recent, homebridge://status. Changes arrive over the Homebridge UI's socket.io namespaces, or by polling when the socket can't be used.
MCP resource templates (listed in resources/list, with completion): homebridge://accessory/{uniqueId} (one accessory with every characteristic), homebridge://plugin/{name} (one installed plugin and its child bridges; URL-encode scoped names), homebridge://child-bridge/{id} (one child bridge by username, with its health on Glass UI).
MCP prompts: diagnose-logs, plan-upgrade, audit-config, troubleshoot-device (device, symptom?), nightly-health-check (hours?), scene-builder (description, room?).
Assistant features (library): diagnoseLogs, generatePluginConfig, explainDeviceError, assessPluginUpdate, suggestOrganization, dailyDigest, ask, and runAgent for anything that needs the tools. Every input is redacted before it reaches a provider and trimmed to fit its context window; JSON outputs are checked against a schema with one automatic repair attempt; token usage and Claude costs are tracked.
All providers use plain fetch (no SDKs). Each declares what it can do, and features without tool calling fall back to prompt-only answers.
provider | Default model | API key | Tools | Streaming | Context |
|---|---|---|---|---|---|
anthropic | claude-sonnet-5-5 | required | yes | yes | 1M (200K for Haiku) |
openai | gpt-6.1-sol | required | yes | yes | 128K (set contextTokens for more) |
gemini | gemini-3.8-flash | required | yes | yes | 1M |
openai-compatible | llama3.1 | optional | yes | yes | 8K (set contextTokens) |
claude-sonnet-5-5 (default), claude-haiku-4-5-20251001 (cheapest), claude-opus-5-5 (most capable).gpt-6.1-sol (default), gpt-6-luna (cheapest), gpt-6-astra (most capable). Requests use the Responses API with store: false (nothing is kept on OpenAI's side); newer models only call tools through it. Set "openaiApi": "chat" to use Chat Completions instead, e.g. for a proxy that only speaks it.openai-compatible works with Ollama (http://127.0.0.1:11434/v1, the default), LM Studio (http://127.0.0.1:1234/v1), vLLM and similar. Set contextTokens to your model's context window so inputs are trimmed correctly.Install it like any plugin (Homebridge 1.8+ or 2.x):
npm install -g @mp-consulting/homebridge-ai-kit
Then open its settings in the Homebridge UI. The settings page edits the HomebridgeAiKit platform block, tests the connection with the values in the form, and shows ready-to-paste configs for Claude Desktop, Claude Code and Cursor.
{
"platform": "HomebridgeAiKit", "name": "AI Kit", "enabled": true, "provider": "anthropic", // anthropic | openai | gemini | openai-compatible "model": "claude-sonnet-5-5", // optional, defaults per provider "apiKey": "sk-ant-…", // secret, redacted wherever config is shown to a model "baseUrl": "http://127.0.0.1:11434/v1", // openai-compatible only (or a proxy) "contextTokens": 32768, // optional override, mainly for local models "maxOutputTokens": 2048, "effort": "medium", // Claude and OpenAI: low | medium | high | xhigh | max (unset = model default) "openaiApi": "responses", // openai / openai-compatible: responses | chat (default responses for OpenAI, chat for local servers) "maxRetries": 2, // retries on 408/429/5xx/529 and network errors (backoff, honours retry-after); 0 = off "mcp": { "http": { "enabled": false, "host": "127.0.0.1", "port": 8582, "token": "…", // bearer token MCP clients must send "homebridgeUrl": "http://127.0.0.1:8581", "homebridgeToken": "hbg_…", // Glass UI API token the tools act with "homebridgeTokenId": "…", // written by Glass UI so it can revoke that token; leave as is "homebridgeCertFingerprint": "AB:CD:…", // https UI with a self-signed certificate: its SHA-256 fingerprint "homebridgeCertPath": "/path/to/certificate.pem", // or a PEM with the UI's certificate or its CA "readOnly": false, // true caps every client token at read-only "clients": [ // more client tokens, each with a scope: read | control | admin { "name": "Dashboard", "token": "…", "scope": "read" } ], "allowedOrigins": ["https://my-dashboard.local"], // browser pages allowed besides localhost / this server's IP "auditLog": true, // log every write tool call (JSONL) "auditLogPath": "/var/lib/homebridge/homebridge-ai-kit-audit.jsonl" // default: Homebridge storage path } } }
With mcp.http.enabled, the plugin serves MCP at http:// : /mcp while Homebridge runs. It needs a client token (mcp.http.token, HOMEBRIDGE_AI_MCP_TOKEN, or at least one scoped token in mcp.http.clients) and Homebridge credentials: a Glass UI API token in homebridgeToken, or the HOMEBRIDGE_* environment variables. A read-only API token gives clients read-only access.
The MCP server uses two different tokens:
| Token | What it is for | Stored in |
|---|---|---|
| Client token | What Claude, Cursor or another MCP client must send (Authorization: Bearer …) to reach the HTTP MCP server. Full access (admin), or read-only with mcp.http.readOnly | mcp.http.token (or HOMEBRIDGE_AI_MCP_TOKEN for the CLI) |
| Scoped client tokens | Optional extra client tokens with less access, e.g. a read-only token for a dashboard | mcp.http.clients (or HOMEBRIDGE_AI_MCP_TOKENS for the CLI) |
| Homebridge API token | What the MCP server sends to the Homebridge UI to run its tools. Its scope decides what clients can do: read gives read-only tools, admin gives all of them | mcp.http.homebridgeToken (or HOMEBRIDGE_TOKEN for the CLI) |
Where to set or generate them:
HOMEBRIDGE_AI_MCP_TOKEN and HOMEBRIDGE_TOKEN (see MCP server), e.g. HOMEBRIDGE_AI_MCP_TOKEN=$(openssl rand -base64 24).Client token scopes (each includes the ones before it):
| Scope | Tools |
|---|---|
read | Every read-only tool |
control | Plus device control: set_accessory, set_security_accessory (locks still need the user's confirmation), set_accessories, run_scene |
admin | Plus everything else: config writes and restores, backups, save_scene, test notifications, plugin installs and updates, restarts, cached accessories, child bridges |
The main client token is admin (as before), or read when readOnly is on; readOnly caps the scoped tokens too. A session belongs to the token that opened it. The client token decides which tools a client sees; the Homebridge API token still limits what the server itself can do, so a read API token keeps everything read-only.
Every write tool call is appended to an audit log ( /homebridge-ai-kit-audit.jsonl by default; mcp.http.auditLog / auditLogPath, or HOMEBRIDGE_AI_AUDIT_LOG for the CLI): one JSON object per line with ts, tool, args (secrets redacted), ok, error, session, client, principal (the token's name: default for the main token, agent for runAgent) and scope; notConfirmed: true marks a destructive call the user declined (MCP elicitation, or runAgent's confirm), which did not run. Dry runs are logged too, with dryRun: true in args. runAgent takes the same audit option. It rotates at 5 MB and keeps three old files.
Glass UI also stores homebridgeTokenId, the id of the API token it created, so it can revoke the token when you replace or remove it. The settings page keeps it (and any other field it doesn't show) when it saves.
Node refuses a self-signed certificate, so the MCP server can't reach a Homebridge UI served that way until you tell it which certificate to trust. Verification is never turned off: the setting only appli
Solo se muestra el principio; lee el resto en el repo