What is rba-mcp CLAUDE.md?

A project instruction file for the rba-mcp repository, an MCP server that provides Reserve Bank of Australia statistics. It documents the data sources, supported datasets, required Python modules, and repository-specific rules.

Use it when developing, reviewing, or troubleshooting rba-mcp. It helps guide changes to the server, data models, curated datasets, caching, and related Python modules.

It gives a coding agent the context needed to work safely in that particular codebase instead of guessing how its files and data fit together. It also explains details such as F-table CSV downloads and the included interest-rate and foreign-exchange datasets.

How Bigred97/rba-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Bigred97/rba-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/Bigred97/rba-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Bigred97/rba-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/bigred97/rba-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/bigred97/rba-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/bigred97/rba-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bigred97/rba-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/bigred97/rba-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/bigred97/rba-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 644 This file is loaded in full into every session.

When invoked 644 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	$0.00644	$0.00644
Opus 5.5	$0.00258	$0.00258
Sonnet 5.5	$0.00129	$0.00129
Haiku 4.5	$0.00064	$0.00064

Measured 2mo ago against content hash 09b625e252a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rba-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 2mo 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 · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rba-mcp

Sister MCP in the Australian Public Data stack. See ../CLAUDE.md for portfolio-wide conventions (tool surface, trust contract, quality bar, test taxonomy, anti-patterns, release process — read it even though this session may not auto-load it if started inside this repo). Use the sister-release skill for releases.

Source


Source agency	Reserve Bank of Australia (RBA)
Source URL	https://www.rba.gov.au/statistics/tables/
Data format	F-table CSV downloads
Licence	CC-BY 4.0 International
Licence URL	https://creativecommons.org/licenses/by/4.0/
Python module	`rba_mcp`
PyPI package	`rba-mcp`
GitHub	https://github.com/Bigred97/rba-mcp

Curated datasets (15)

F1.1 (money market) · F2 (govt bond yields daily) · F2.1 (govt bond yields monthly) · F4 (deposit/inv rates) · F5 (indicator lending rates) · F6 (housing lending) · F7 (business lending rates) · F8 (personal lending rates) · F11 (FX monthly) · F11.1 (FX daily) · D1 (credit growth) · D2 (credit aggregates levels) · C1 (credit-card statistics) · G3 (inflation expectations) · E2 (household leverage ratios)

Repo-specific module set

Extras beyond the standard sister module set (see parent): parsing.py — F-table CSV reader (rows 1-5 are metadata, row 11 is series ID, data starts row 12); tables.py — F-table registry (currently 5 curated, ~50 published).

Repo-specific gotchas

F-table CSVs have a non-standard header — row 6 is Units, row 11 is Series ID (NOT row 5 / row 8 as generic RBA docs suggest).
Tool names diverge from the parent's standard search_*/describe_* pattern by design: search_tables / describe_table, because the data shape is tables-not-datasets.
end_date snaps to the LAST instant of its period (so end_date='2024' includes all of 2024, not just Jan 1).
Trusted Publishing was set up in 0.1.6 — first sister to do so.
top_n is intentionally absent. F-table CSVs are flat series-by-time matrices — each series ID is its own column, with no entity dimension to rank across. Adding top_n would require synthesising a "top series" concept that isn't natively meaningful on F-tables. Customers wanting comparative views should use describe_table() to see available series and call get_data() with the series IDs they care about.

Read the full file on GitHub · 45 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.

2mo ago Changed · -89 lines · -1,272 tokens per session 09b625e252a4
2mo ago First seen · 134 lines · 1,916 tokens per session scan A 13e6283727ae

Subscribe to this mod's changes

rba-mcp CLAUDE.md is an instructions file published in the GitHub repository Bigred97/rba-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 644 tokens to every session, about $0.0026 per session on Opus 5.5. 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 australia interest-rates mcp mcp-server model-context-protocol rba

rba-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rba-mcp CLAUDE.mdBigred97/rba-mcp	Instructions file	0	1mo ago	MIT	A	644	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

rba-mcp: Instructions file for Claude Code