UK Rates & Thresholds — open dataset

108 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 108 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).

Related MCP server: UK Parliament MCP Server

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 by id (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 own source_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.