benny-the-dog-mcp
MCP server for Benny the dog's health and care monitoring, allowing users to log care events like water refills, barks, movement, sausage deliveries, movie time, and wake calls, with automatic loneliness detection and Boomy robot integration.
README
benny-the-dog-mcp
Benny the dog health and care monitor - water bowls, movement, loneliness detection, sausage deliveries, projector movie time, wake calls. Boomy-robot patrol integration ready.
Fleet-standard fullstack app: FastMCP 3.4 backend, React + Vite + Tailwind frontend, Bun, optional Tauri 2.0 desktop wrapper.
Quick start
uv sync
bun --prefix webapp install
.\start.ps1 # clears ports, starts backend + frontend, opens browser
- Backend API + Swagger: http://127.0.0.1:11142/docs
- Frontend: http://127.0.0.1:11143
- MCP endpoint (when enabled): http://127.0.0.1:11142/mcp
What it does
- Care events: log water refills, barks, movement, sausage deliveries, projector movie time, and wake calls via the
dog_opsMCP tool. - Loneliness detection: the 5-minute patrol job (APScheduler) flags barks with no subsequent movement and suggests a sausage delivery.
- Dog profile: 6-step onboarding wizard (bio, photos, vet & health, behaviour, walking, dogparks/fountains).
- Webapp: Dashboard, Tools, Skills, Chat (local LLM), Vet & Health, Settings, Help, Logs, ApiDocs, Jobs, Dog Partners, Shop, Cart, Onboarding.
- Robot-ready:
actor="boomy"on every event for the Boomy robot patrol.
Tools
| Tool | Description |
|---|---|
dog_ops |
Care portmanteau: status, water_refill, bark_event, movement, sausage_delivery, movie_time, wake |
app_info |
Server metadata (name, version, tool count) |
server_shutdown |
Graceful shutdown (confirm=True required) |
Full reference: docs/TOOLS.md | llms-full.txt
Claude Desktop config
{
"mcpServers": {
"benny": {
"command": "uv",
"args": ["run", "--directory", "D:/Dev/repos/benny-the-dog-mcp", "python", "-m", "benny_the_dog_mcp.server"]
}
}
}
Environment
Copy .env.example to .env. See docs/CONFIGURATION.md for the full table.
| Variable | Default | Purpose |
|---|---|---|
WEB_PORT |
11142 |
Backend port |
OLLAMA_URL |
http://127.0.0.1:11434 |
Chat LLM endpoint |
ENABLE_SCHEDULER |
1 |
Patrol job (5 min) |
Ports
Registered in the fleet reservoir: backend 11142, frontend 11143 (see mcp-central-docs/operations/WEBAPP_PORTS.md).
Tests
uv run pytest tests/ # backend (73% coverage)
bun --prefix webapp run e2e # Playwright
Documentation
- docs/CONFIGURATION.md — env vars, ports, storage
- docs/DEVELOPMENT.md — stack, layout, commands, gates
- docs/TOOLS.md — MCP tools + REST API reference
- docs/TROUBLESHOOTING.md — common issues
- docs/ONBOARDING.md — dog onboarding wizard
- llms.txt / llms-full.txt — LLM reference
- CHANGELOG.md
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.