TN Trustee MCP

TN Trustee MCP

Read-only MCP server for public Tennessee property-tax information, with SQLite caching and support for Cheatham and Stewart counties.

Category
访问服务器

README

TN Trustee MCP

Read-only MCP access to public Tennessee property-tax information.

[!IMPORTANT] This project does not submit property-tax payments and does not access the payment cart. It retrieves and normalizes public-facing information only. Amounts shown exclude interest and are not payoff totals. Confirm any amount owed with the county trustee before paying.

The project is in Phase 1. It currently provides configuration, normalized data contracts, SQLite persistence, a command shell, and an MCP STDIO server shell with zero registered tools. It does not yet contact TennesseeTrustee.org.

Requirements

  • Python 3.12 or later
  • uv
  • An operator contact string for the descriptive user agent

Setup

uv python install 3.12
uv sync --extra dev
Copy-Item .env.example .env

Replace operator@example.com in .env with a monitored contact address. The required variable name is TN_TRUSTEE_USER_AGENT_CONTACT.

Initialize the local database:

uv run tn-trustee-mcp db init

List configured entities without contacting the source:

uv run tn-trustee-mcp entities list

Entity configuration keeps the landing and search URLs separate. entity_path contains the entity query parameter. search_path is the query-free /search.php endpoint.

Start the Phase 1 MCP shell:

uv run tn-trustee-mcp serve

Development checks

uv run ruff check .
uv run ruff format --check .
uv run mypy
uv run pytest
uv run python -m build

CLI tests inspect the registered command tree directly so option visibility is validated consistently on Windows and Linux.

Project reference

See assessment.md for the current phase, implemented components, open questions, validation baseline, and next action. Contributors and coding agents maintain it with every delivered repository change.

Every delivered repository change must update CHANGELOG.md, assessment.md, and this README. The changelog records what changed. The assessment provides a quick current-state reference. The README must stay aligned with the current setup, behavior, scope, and operator instructions.

Current scope

  • Cheatham County and Stewart County configuration only
  • HTTPS query parameter routes through tennesseetrustee.org
  • Separate validated entity landing and search paths
  • Public, read-only property-tax information
  • Local SQLite cache and future snapshot storage
  • Visible Phase 1 CLI stubs for search, record, snapshot, and source-status commands

Search behavior and HTML parsing are intentionally absent until the Phase 2 source inspection is complete.

Safety

The server must never access cart, checkout, or payment endpoints. It must never submit payments, bypass authentication or CAPTCHA, disable certificate validation, or perform bulk owner-name harvesting. See SECURITY.md and docs/COMPLIANCE.md.

License

See LICENSE.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选