Skip to main content
Glama

HomeOps

HomeOps is an agent-ready household maintenance memory built for the 2026 WebMCP Challenge.

It turns routine home upkeep into structured, browser-native tools that people and AI agents can use together. A homeowner sees a simple maintenance brief; an agent can inspect due work, look up service history, add recurring responsibilities, log completed maintenance, and create a prioritized plan without guessing its way through the interface.

Live demo

https://homeops-webmcp.vercel.app

The hosted challenge build is static, requires no account or API key, and stores demo data locally in the browser.

Related MCP server: household-agent

Why HomeOps

Home maintenance rarely fails because the work is technically difficult. It fails because dates, filter sizes, service notes, and recurring intervals are scattered across memory, paper manuals, and disconnected apps.

HomeOps creates one shared household record:

  • People can see what needs attention and when.

  • Agents can call explicit tools instead of scraping or clicking blindly.

  • Read and write actions operate on the same state shown in the UI.

  • Changes made by an agent are immediately visible to the person.

WebMCP tools

The challenge build registers these tools with the browser's WebMCP interface when available:

Tool

Purpose

State change

homeops_list_due

List overdue and upcoming maintenance within a horizon

No

homeops_lookup_item

Retrieve service history, notes, and next due date

No

homeops_log_service

Record completed maintenance and update the dashboard

Yes

homeops_add_item

Add a new recurring household responsibility

Yes

homeops_plan_next

Return a prioritized maintenance action plan

No

The page also remains fully usable in browsers that do not expose WebMCP yet.

Human-agent experience

Example mission:

Audit my home for the next 30 days, tell me the top three things to handle, and record that I changed the HVAC filter today.

An agent can:

  1. Call homeops_plan_next to create the priority list.

  2. Explain the recommendations to the homeowner.

  3. Call homeops_log_service after confirmation.

  4. Leave the visible dashboard and agent-readable state synchronized.

Repository structure

webmcp-static/          Hosted WebMCP challenge entry
  index.html
  styles.css
  app.js
public/                 Original interactive prototype UI
lib/                    Maintenance logic and tool definitions
server.js               Local MCP + demo server
tests/                  Node test suite
submission/             Submission copy and demo materials
.github/workflows/      Automated tests

Run the full local prototype

Requirements: Node.js 20+.

npm start

Then open:

http://localhost:8787

The local MCP endpoint is:

http://localhost:8787/mcp

Test

npm test

No npm packages or paid API keys are required.

Architecture

Person / browser agent
          |
          v
HomeOps browser interface
          |
          +--> WebMCP tool registration
          |
          +--> Shared maintenance state
          |
          +--> Visible maintenance brief

Local prototype also exposes:
          |
          v
MCP Streamable HTTP endpoint

Privacy and safety

  • Hosted challenge data stays in browser local storage.

  • The project does not require account credentials or financial information.

  • Tools are narrowly scoped to household maintenance records.

  • Read-only and state-changing tools are clearly separated.

  • The demo contains no purchasing or irreversible real-world actions.

Challenge

Built for The WebMCP Challenge, with judging centered on usefulness, originality, execution, thoughtful WebMCP use, and the quality of the human-agent experience.

License

MIT

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • F
    license
    A
    quality
    C
    maintenance
    Enables AI agents to automate property maintenance workflows by managing tickets, sending WhatsApp notifications via Twilio, and triggering n8n automation webhooks. It allows users to query maintenance statuses, notify tenants, and escalate issues to vendors using natural language.
    4
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI clients to manage field service operations through natural language, including call handling, job dispatch, estimates, invoicing, and reporting via the AutoRev platform.
    54
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables natural-language read and write access to a Homebox inventory, including searching and managing items, locations, tags, and attaching files such as receipts and warranties.
    MIT

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/BurpingSpider/homeops-mcp'

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