What is israel-statistics-mcp CLAUDE.md?

Project instructions for an MCP server that provides read-only access to Israeli Central Bureau of Statistics price indexes. An MCP server is a program that lets an AI assistant call defined tools.

Use them when developing or maintaining this server, running its checks, testing its tools, building its package, or running smoke tests against the CBS data service.

They document how to build, check, test, lint, format, and run the server, including the difference between offline tests and optional live API tests. They also describe the server's source structure and operational constraints.

How reuvenaor/israel-statistics-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to reuvenaor/israel-statistics-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/reuvenaor/israel-statistics-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/reuvenaor/israel-statistics-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/reuvenaor/israel-statistics-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/reuvenaor/israel-statistics-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/reuvenaor/israel-statistics-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/reuvenaor/israel-statistics-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/reuvenaor/israel-statistics-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/reuvenaor/israel-statistics-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,451 This file is loaded in full into every session.

When invoked 1,451 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.

Model	Per session	Once invoked
Fable 5.1	$0.01451	$0.01451
Opus 5	$0.00726	$0.00726
Sonnet 5	$0.00290	$0.00290
Haiku 4.5	$0.00145	$0.00145

Measured 11d ago against content hash 413f9c1a4953, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

israel-statistics-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 11d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

israel-statistics-mcp

Stdio MCP server exposing Israeli CBS (Central Bureau of Statistics) price indices: 9 read-only tools for catalog discovery, index data, main indices, and inflation-linkage calculation. Published to npm (@reuvenorg/israel-statistics-mcp), Docker Hub (reuvenaor/israel-statistics-mcp), and the official MCP Registry (io.github.reuvenaor/israel-statistics-mcp).

Commands

pnpm build            # tsup → dist/ (ESM, shebang bin)
pnpm typecheck        # tsc --noEmit
pnpm test             # unit tests ONLY — always offline (prepublishOnly runs this)
pnpm test:live        # live CBS API suite (opt-in; slow; needs network)
pnpm lint / lint:fix  # eslint flat config
pnpm format:write     # prettier
pnpm smoke            # scripts/smoke.mjs — Inspector CLI offline smoke (tools/list = 9)
node scripts/smoke.mjs --live       # smoke with real CBS tool calls
node scripts/smoke.mjs --command "docker run --rm -i israel-statistics-mcp:dev"  # smoke any spawn form

Architecture

src/index.ts            entry: shebang, createServer + StdioServerTransport, graceful shutdown
src/server.ts           createServer(): registers TOOLS table, server instructions
src/mcp/tools.ts        the 9-tool table: name/title/description/inputSchema/outputSchema/handler
src/mcp/handlers/       one handler per tool → builds params → secureFetch → transform + summary
src/mcp/helpers/fetcher.ts    secureFetch: the ONLY network path (timeout/UA/retry/host allowlist)
src/mcp/helpers/housingWarnings.ts  bi-monthly housing provisional-window warnings
src/mcp/helpers/semaphore.ts  FIFO concurrency limiter (5 concurrent, 50 queued)
src/schemas/            zod v3: request (inputs), response (CBS shapes), output (structuredContent)
src/pkg.ts              VERSION single-source (package.json) — used by serverInfo + User-Agent

Hard constraints (violating these breaks users)

stdio protocol: stdout is JSON-RPC only. All logging via console.error (stderr). Never console.log.
SDK 1.x ⇒ zod v3 line only (zod ^3.25.76). zod 4 breaks the SDK — do not upgrade until we migrate to SDK v2 (GA).
Never declare MCP capabilities without handlers. McpServer auto-derives capabilities from registrations. A hand-written capabilities:{logging:{},resources:{}} block shipped in v0.0.2 made MCP Inspector unable to connect (logging/setLevel → -32601).
Tool names and accepted params are a published API — additive changes only; never rename/remove/retype.
Tool responses return both content:[{type:"text", text: JSON.stringify(result)}] and structuredContent: result. Output schemas are validated by the SDK on every call — keep them tolerant of CBS variance (nullable numerics, loose date strings).
Server version comes from src/pkg.ts (package.json) — never hardcode.

Read the full file on GitHub · 67 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.

11d ago First seen · 67 lines · 1,451 tokens per session scan A 413f9c1a4953

Subscribe to this mod's changes

israel-statistics-mcp CLAUDE.md is an instructions file published in the GitHub repository reuvenaor/israel-statistics-mcp (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,451 tokens to every session, about $0.0073 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.

Analytics and metrics

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

israel-statistics-mcp: Instructions file for Claude Code