uk-rates-thresholds
Query current and historical UK official figures (tax bands, minimum wage, benefits, energy price cap and 100+ more) with effective dates and links to official government sources. Data refreshed whenever the official sources change.
README
UK Rates & Thresholds — open dataset
133 current UK official figures — Income Tax, National Insurance, benefits, wages, pensions, savings, energy and government fees — each effective-dated and linked to its official source. Built and kept fresh for rates.trycashpilot.com.
Data, not advice. Verify with the linked official source before acting.
What's here
data/*.yaml— the 133 figures. Every entry is self-describing:- id: income_tax_personal_allowance name: Income Tax Personal Allowance category: tax value: "£12,570" unit: per year valid_from: "2026-04-06" valid_to: "2027-04-05" source_url: https://www.gov.uk/income-tax-rates source_org: HMRC / gov.uk confidence: verified # checked against the official page checked_at: "2026-08-11" notes: "..." history: ["£12,570 from 2021-04-06", "..."]mcp/server.py— a Model Context Protocol server so AI agents can query the figures directly (below).
How to use it
- Website — https://rates.trycashpilot.com — one page per figure, answering "what is X right now?", each sourced and dated.
- JSON API — https://rates.trycashpilot.com/api/v1/all.json — every figure, machine-readable (
count+metrics[]). - This repo — clone the YAML and use it directly.
MCP server (for AI agents)
mcp/server.py speaks the Model Context Protocol over stdio (JSON-RPC 2.0), with no dependencies beyond PyYAML. It gives an agent three tools:
list_metrics— every figure (id, name, category, current value)get_metric— one figure byid(value, validity dates, official source URL, history)search_metrics— by keyword (e.g.minimum wage,ISA,price cap)
Run it:
pip install pyyaml
python3 mcp/server.py
Then register it in your MCP client (e.g. Claude Desktop mcpServers):
{
"mcpServers": {
"uk-rates-thresholds": {
"command": "python3",
"args": ["/absolute/path/to/mcp/server.py"]
}
}
}
Licence
- Data (
data/) contains public sector information licensed under the Open Government Licence v3.0. Figures are drawn from GOV.UK / HMRC / DWP / Ofgem / the Bank of England and other official sources; each entry links its ownsource_url. Attribution: "Contains public sector information licensed under the Open Government Licence v3.0." - Code (
mcp/and tooling) is MIT.
Disclaimer
This is a data reference, not tax, legal or financial advice. Figures change; always confirm the current value with the linked official source before acting.
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。