property-inventory
Provides a local-first, evidence-backed ledger for physical property, enabling agents to search inventory, prepare capture reviews, and inspect proposals through MCP. Enforces strict boundaries: scoped reads by default, with private write access limited to preparing, not applying, mutations.
README
agent-property-inventory
agent-property-inventory is a local JSONL ledger that lets agents answer what you own, where it is, and what it works with.

Agents query before buying or advising. Facts enter through one verified local writer.
What it knows
The ledger preserves photos, receipts, serials, locations, condition, measurements, lifecycle history, and unknowns. An empty search means “not recorded,” never “does not exist.”
How it works
Data/store/*.jsonl is the sole source of truth. Immutable media, runtime databases, and backups stay outside Obsidian. SQLite and Inventory.md are disposable rebuilt views.
Quick start
Python 3.11 or newer is required.
git clone https://github.com/Anneo22/agent-property-inventory.git
cd agent-property-inventory
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -e '.[dev,mcp]'
demo_root="$(mktemp -d "${TMPDIR:-/tmp}/property-inventory-demo.XXXXXX")"
export PROPERTY_INVENTORY_ROOT="$demo_root/inventory"
export PROPERTY_INVENTORY_RUNTIME="$demo_root/runtime"
export PROPERTY_INVENTORY_MEDIA_ROOT="$demo_root/media"
export PROPERTY_INVENTORY_CATALOGUE_OUTPUT="$demo_root/notes/Inventory.md"
property-inventory init
property-inventory status
status rebuilds SQLite, regenerates the catalogue, runs the semantic verifier, and checks every foreign key.
Use it
Query before buying or claiming ownership:
property-inventory search "hex bit" --condition working
property-inventory context --task "repair a bicycle tyre"
property-inventory compatibility itm-driver itm-bit
property-inventory torque-check --tool-item-id itm-driver --requested-nm 4
Record a real check against an existing item and location:
property-inventory physical-check \
--actor "Example reviewer" \
--source-ref "Checked in person" \
--item-id itm-example \
--checked-on 2026-08-09 \
--location-id loc-example \
--quantity 1 \
--condition working
The CLI also records plans, orders, deliveries, moves, loans, sales, corrections, evidence, kits, maintenance, insurance readiness, measured spaces, and offline replica proposals. Run property-inventory --help for the complete command surface.
Connect an agent
The MCP server is a local stdio process. Its default read profile can search, inspect, and reason about the inventory without changing canonical JSONL.
{
"command": "/absolute/path/to/property-inventory-mcp",
"args": [
"--config", "/absolute/path/to/config.json",
"--instance", "private",
"--scope", "personal",
"--profile", "read"
]
}
The private write profile may prepare bounded proposals, capture reviews, and replica plans. It cannot apply them or invoke direct lifecycle mutations. See MCP profiles.
Deliberate limits
There is no web or phone interface, hosted sync service, bundled recognition model, insurer integration, or proof of broad real-world adoption. Spatial packing is a deterministic measured-box heuristic, not an optimal organizer. Local capture adapters are trusted programs and still require explicit review.
Documentation
Development
ruff check .
python3 -m compileall -q src property_inventory.py rebuild_inventory_sqlite.py render_inventory.py verify_inventory.py
python3 -m unittest discover -v -s tests -p 'test_*.py'
vhs docs/assets/demo.tape
python3 scripts/check-readme-visuals.py
scripts/check-public-leaks.sh
License
MIT. See LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。