mcp-nb: Instructions file for Claude Code

CLAUDE.md

mcp-nb CLAUDE.md is an instructions file for Claude Code from mctar/mcp-nb. It costs 938 tokens per session, scanned A, original, MIT.

A set of project instructions for working on an MCP server that gives AI agents access to Norges Bank's open economic data. Norges Bank is Norway's central bank, and open data is information available for public use.

In plain words
What is it for?
Use it when developing or maintaining the server, which provides exchange rates, interest-rate, debt, money-market, bank-liquidity, and survey data through an HTTP service.
Why use it?
It gives developers a common way to run, understand, and modify the project, including its data flow, files, server setup, and testing status.

Instructions file for Claude Code

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

This is mctar/mcp-nb's own configuration. It tells Claude Code how to work on mcp-nb 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 mcp-nb configures →

View source ↗ mctar/mcp-nb
Reuse

Borrowing it

Nothing to install: this file belongs to mctar/mcp-nb. 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/mctar/mcp-nb/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mctar/mcp-nb

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 mcp-nb CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mctar/mcp-nb/claude-md/github.svg)](https://agentmods.dev/instructions/mctar/mcp-nb/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mctar/mcp-nb/claude-md"><img src="https://agentmods.dev/badge/instructions/mctar/mcp-nb/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 mcp-nb CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mctar/mcp-nb/claude-md"><img src="https://agentmods.dev/badge/instructions/mctar/mcp-nb/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 938 This file is loaded in full into every session.
When invoked 938 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 $0.00938 $0.00938
Opus 5.5 $0.00375 $0.00375
Sonnet 5.5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured 2mo ago against content hash 4d438c98eacf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-nb 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

An MCP (Model Context Protocol) server that gives AI agents access to Norges Bank's open data API. Covers exchange rates, policy rate, government debt, money market data, bank liquidity, and the Regional Network survey. Built by Gervi Labs alongside MCP servers for SSB and FHI.

Running

pip install -r requirements.txt
python server.py

Or with Docker:

docker compose up

Server runs on port 8007 (streamable HTTP). No auth required on either side.

There are no tests in this project.

Architecture

Framework: FastMCP | Transport: streamable HTTP on port 8007 | Upstream: Norges Bank SDMX 2.1 REST API at https://data.norges-bank.no/api/

Data flow

server.py creates a FastMCP instance and registers tools/prompts from tools.py and entry_prompt.py using mcp.tool()() / mcp.prompt()(). Tools call NorgesBankClient (in client.py), which makes HTTP requests to the SDMX API. Config constants and currency aliases live in config.py.

Import pattern

All internal imports use a try/except pattern (from .module falling back to from module) so the code works both as a package and when run directly with python server.py.

Tool design

Progressive discovery pattern: discover (nb_list_dataflows) -> explore (nb_get_dataflow_structure) -> query (nb_get_data). Two convenience wrappers (nb_get_exchange_rate, nb_get_policy_rate) handle the most common use cases. nb_get_api_status is a health check.

All tools return human-readable pipe-separated text tables, not raw SDMX JSON. The SDMX-JSON parsing in _parse_sdmx_json_data decodes positional indices (series keys like "0:1:0:0" and observation keys like "0") into dimension labels and dates. Output is capped at 500 rows.

Currency resolution

nb_get_exchange_rate accepts ISO codes or common names ("dollar", "euro", "pound"). Aliases are in the CURRENCY_ALIASES dict in config.py. Resolution: lowercase input -> alias lookup -> fallback to 3-letter uppercase as ISO code.

Read the full file on GitHub · 73 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. 2mo ago First seen · 73 lines · 938 tokens per session scan A 4d438c98eacf

Subscribe to this mod's changes

mcp-nb CLAUDE.md is an instructions file published in the GitHub repository mctar/mcp-nb (0 stars, last pushed 7mo ago), licensed MIT. It adds 938 tokens to every session, about $0.0038 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.

Related

mcp-nb CLAUDE.md compared with instructions from other repositories

mcp-nb CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-nb CLAUDE.mdmctar/mcp-nbInstructions file07mo agoMITA938Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode