AllOurThings MCP Server

AllOurThings MCP Server

Enables cataloging and managing personal inventory (items, attachments) through natural language, allowing users to add, search, update, and retrieve item details and attachments via MCP tools.

Category
Visit Server

README

AllOurThings

Your things, understood by AI.

AllOurThings is an inventory system that works the way you do. Catalog anything you like from your home appliances to your Pokémon cards — then ask plain-English questions and get instant answers.

Website: allourthings.io

Packages

Package npm Description
packages/mcp-server @allourthings/mcp-server MCP server — connects your inventory to Claude Desktop and other MCP clients
packages/cli @allourthings/cli CLI — manage your inventory from the terminal

Quick start

Desktop only. Requires macOS, Windows, or Linux with Claude Desktop or another MCP-compatible client.

1. Add to Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "allourthings": {
      "command": "npx",
      "args": ["-y", "@allourthings/mcp-server", "--data-dir", "~/Documents/AllOurThings"]
    }
  }
}

Restart Claude Desktop. Your inventory vault will be created automatically on first use.

2. Start asking questions

  • "Add my Bosch washing machine, bought from John Lewis for £649 in January 2024 with a 2-year warranty"
  • "What appliances do I own?"
  • "What's in the kitchen?"
  • "When does my TV warranty expire?"
  • "Search for anything Samsung"
  • "How much have I spent on electronics?"

How it works

The MCP server exposes your inventory to any MCP-compatible AI client via 10 tools:

Tool Description
add_item Add a new item to your inventory
get_item Retrieve an item by ID or name
list_items List all items, optionally filtered by category, location, or tags
update_item Update fields on an existing item
delete_item Delete an item by ID
search_items Full-text search across all item fields
add_attachment Attach a file (manual, receipt, photo, warranty) to an item
get_attachment Retrieve an attachment as base64
delete_attachment Remove an attachment from an item
attach_from_url Download a file from a URL and attach it to an item

Data

Vault structure

Your inventory lives in a vault — a plain directory on your filesystem. Each item gets its own folder:

~/Documents/AllOurThings/
  items/
    dyson-v15-detect-a1b2c3d4/
      item.json
      manual.pdf
      receipt.jpg
    samsung-65-qled-tv-b5c6d7e8/
      item.json
      warranty.pdf

Attachments (manuals, receipts, photos) sit alongside the item JSON. You can browse and edit the vault directly in Finder or File Explorer.

Item schema

Every item has required fields (id, name, created_at, updated_at) and well-known optional fields:

category brand model purchase_date purchase_price currency warranty_expires retailer location features notes tags attachments

The attachments field links PDFs and images stored in the item's folder:

{
  "attachments": [
    { "filename": "manual.pdf",  "type": "manual"   },
    { "filename": "receipt.jpg", "type": "receipt"  },
    { "filename": "photo.jpg",   "type": "photo"    }
  ]
}

You can also add any custom fields you like — they are preserved as-is.


CLI

A standalone terminal tool for power users and scripting. Works on macOS, Windows, and Linux. No AI client required.

# Run without installing
npx @allourthings/cli list

# Or install globally
npm install -g @allourthings/cli

Commands

allourthings search <query>                          # full-text search across all fields
allourthings list [--category <c>] [-l <loc>] [-t <tag>]  # list items, optionally filtered
allourthings get <id-or-name>                        # show full item detail
allourthings add <name> [options]                    # add a new item
allourthings update <id> [options]                   # update item fields
allourthings delete <id>                             # delete an item (prompts for confirmation)

Attachment management:

allourthings attach add <item-id> <file>             # attach a local file to an item
allourthings attach url <item-id> <url>              # download a file and attach it
allourthings attach get <item-id> <filename>         # save an attachment to disk
allourthings attach rm  <item-id> <filename>         # delete an attachment

add and update options:

-c, --category <category>
-b, --brand <brand>
-m, --model <model>
    --purchase-date <date>    ISO date, e.g. 2024-01-15
    --price <price>
    --currency <currency>     e.g. GBP, USD
    --warranty <date>         warranty expiry ISO date
    --retailer <retailer>
-l, --location <location>
    --serial <serial>
-t, --tag <tag...>            repeatable
-n, --notes <notes>
    --set key=value           custom/extra fields (update only, repeatable)

Global options:

--data-dir <path>    path to inventory data directory (default: ~/Documents/AllOurThings)
--json               output raw JSON — useful for scripting and agent use

Data directory: defaults to ~/Documents/AllOurThings on all platforms. To avoid passing --data-dir every time, set it once in your shell profile:

export ALLOURTHINGS_DATA_DIR=~/Dropbox/AllOurThings

The directory is created automatically on first write. Read commands (list, search, get) return empty results against a missing directory rather than erroring.

Examples

# Add an item
allourthings add "Bosch Washing Machine" --brand Bosch --model "WGG244A9GB" \
  --category appliance --location kitchen \
  --purchase-date 2024-01-15 --price 649 --currency GBP \
  --warranty 2026-01-15 --retailer "John Lewis"

# Search and pipe to jq
allourthings search "warranty" --json | jq '[.[] | {name, warranty_expires}]'

# Attach a manual
allourthings attach add 6164c373 ~/Downloads/bosch-manual.pdf --label "User manual"

# Update a field
allourthings update 6164c373 --warranty 2027-01-15

# Use a custom data directory
allourthings --data-dir ~/Dropbox/AllOurThings list

Development

Prerequisites

  • Bunbrew install bun
  • Taskbrew install go-task

Install dependencies

bun install

Tasks

Task Description
task dev Seed vault + open MCP Inspector — fastest way to test
task dev:mcp Start MCP server in watch mode (stdio)
task test:run Run automated tests
task seed Append test items to dev vault
task seed:reset Clear dev vault and re-seed
task inspect Open MCP Inspector (dev mode, no build required)
task inspect:prod Build, then open MCP Inspector against compiled dist
task build Compile MCP server to dist/
task build:cli Compile CLI to dist/
task cli -- <args> Run CLI from source against dev vault, e.g. task cli -- list
task typecheck Run TypeScript type checking
task clean Remove dist/
task clean:vault Delete local dev vault

All tasks use ./dev-vault by default. Override with DATA_DIR=/your/path task <command>.


License

MIT — see LICENSE.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

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.

Official
Featured