boe-mcp: Instructions file for Claude Code

CLAUDE.md

boe-mcp CLAUDE.md is an instructions file for Claude Code from moureauf/boe-mcp. It costs 880 tokens per session, scanned A, original, MIT.

A set of instructions for AI agents working on boe-mcp, a TypeScript server that provides Bank of England interest-rate, economic-series, and meeting-date data.

In plain words
What is it for?
It helps agents build, run, test, lint, and inspect an MCP server that reads public Bank of England data, including the base rate, SONIA, exchange rates, mortgage rates, and MPC meeting dates.
Why use it?
It explains the project's commands, structure, data flow, testing, and network modes so agents can work on the server consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is moureauf/boe-mcp's own configuration. It tells Claude Code how to work on boe-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything boe-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to moureauf/boe-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/moureauf/boe-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/moureauf/boe-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for boe-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/moureauf/boe-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/moureauf/boe-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/moureauf/boe-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/moureauf/boe-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for boe-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/moureauf/boe-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/moureauf/boe-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 880 This file is loaded in full into every session.
When invoked 880 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00880 $0.00880
Opus 5 $0.00440 $0.00440
Sonnet 5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 9d ago against content hash 345c6f738abc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

boe-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

boe-mcp

TypeScript MCP server for Bank of England data: base rate (current, history, stats, historical lookup), any IADB statistical series (SONIA, exchange rates, mortgage rates), and MPC meeting dates. Published to npm as boe-mcp.

Commands

  • npm run build — compile TypeScript to dist/
  • npm run dev — watch mode
  • npm start — run the server
  • npm test — unit tests (no network)
  • npm run test:live — integration smoke test against real BoE endpoints
  • npm run lint — check formatting/lint rules (Biome)
  • npm run lint:fix — apply Biome fixes

Architecture

Claude Code → MCP Server (stdio by default; opt-in Streamable HTTP) → in-memory TTL cache → BoE IADB API

No auth required. All data from public BoE endpoints.

Transports: stdio is the default. HTTP mode is opt-in via --http [port] or BOE_MCP_HTTP_PORT (bind host BOE_MCP_HTTP_HOST, default 127.0.0.1) and runs the SDK's StreamableHTTPServerTransport statelessly — a fresh server per POST.

Project structure

src/ index.ts # thin entry point: transport selection (stdio vs --http) server.ts # createServer(): tool registration (x-release-please-version marker lives here) http.ts # opt-in Streamable HTTP transport (stateless), /mcp + /healthz boe-client.ts # BoE API calls + CSV/HTML parsing cache.ts # generic TTL cache data.ts # shared cached accessors used by the tools series-catalog.ts # curated IADB series catalog + lookup (for list_series) tools/ current-rate.ts rate-history.ts rate-at.ts rate-stats.ts next-meeting.ts mpc-dates.ts list-series.ts get-series.ts test/ # vitest tests + fixtures (test/live/ hits the network) docs/specs/design.md # full design spec — read this first

Tools exposed

Tool Description
get_current_rate Current base rate, effective date, months held
get_rate_history Last N rate changes with basis points (default 10)
get_rate_at Base rate in force on a given historical date
get_rate_stats Min/max/time-weighted average, start/end rates and net bps move over a date range
get_next_mpc_meeting Date of next MPC meeting and days until it
get_mpc_dates All upcoming MPC announcement dates with days until each
list_series Curated catalog of well-known IADB series (code, name, description, unit, frequency)
get_series Observations for any IADB series by code, with optional from/to dates and limit

Read the full file on GitHub · 79 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 79 lines · 880 tokens per session scan A 345c6f738abc

Subscribe to this mod's changes

boe-mcp CLAUDE.md is an instructions file published in the GitHub repository moureauf/boe-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 880 tokens to every session, about $0.0044 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens