What is swiss-public-data-mcp CLAUDE.md?

Repository instructions for an index of Swiss public-data MCP servers. They define a portfolio file as the source of truth and describe checks that verify results instead of merely checking whether a command ran.

Updating the portfolio correctly, regenerating linked documentation, validating coverage, and checking files, exit codes, or other real results.

They prevent false reports caused by testing the wrong thing, editing generated content, or trusting activity without checking its output.

How malkreide/swiss-public-data-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to malkreide/swiss-public-data-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/malkreide/swiss-public-data-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/malkreide/swiss-public-data-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/malkreide/swiss-public-data-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/malkreide/swiss-public-data-mcp/claude-md)

Your own site

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

Per session 2,194 This file is loaded in full into every session.

When invoked 2,194 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	$0.02194	$0.02194
Opus 5.5	$0.00878	$0.00878
Sonnet 5.5	$0.00439	$0.00439
Haiku 4.5	$0.00219	$0.00219

Measured 1mo ago against content hash 912e683390e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swiss-public-data-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 1mo 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 · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project conventions for Claude

This repository is the index for the Swiss Public Data MCP servers. portfolio.json is the source of truth; the READMEs, the registry manifests, the install snippets and the promotion page are generated from it and held to it by readme-sync.yml on every pull request. Never hand-edit anything between  markers — see CONTRIBUTING.md for the edit-and-regenerate loop.

(No server count here on purpose: it would be a hand-copied number in a file about not hand-copying numbers. scripts/coverage_manifest.py --check prints the current one.)

How verification works here

These rules exist because the failures below happened in this portfolio, all within a few days, and all of them the same shape: the check ran and checked nothing. They are not style. Each one produced a confident, false report.

Check the result, not the activity

Never test for a running process with pgrep -f '<your own pattern>'. The pattern is in the command line you are searching with, so pgrep finds itself. Test the result instead: [ -s file ], ls -l, an exit code. A sweep was reported as "still running" twice, two hours after it finished.
Never write command; echo ok. The semicolon separates, it does not connect. Use command && echo ok, or read the state afterwards — the remote ref, the file, the API. A push was reported as done while git was saying the remote end hung up unexpectedly.
In a pipeline, $? is the last command's status. cmd | head reports head. Use ${PIPESTATUS[0]} or drop the pipe.

A pattern that claims absence must first be proven on a known positive

A grep too narrow finds nothing and looks like a clean result. So does a stub that never matches.

Three releases were reported missing because the grep pattern was too narrow. And an exit-code harness reported failure for every case — including the ones that pass — because next(gen, default) evaluates the default eagerly, so the stub raised on every call. A working script was nearly "repaired".

Read the full file on GitHub · 200 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.

1mo ago Changed · -43 lines · -518 tokens per session 912e683390e8
2mo ago First seen · 243 lines · 2,712 tokens per session scan A 8d68edce45a4

Subscribe to this mod's changes

swiss-public-data-mcp CLAUDE.md is an instructions file published in the GitHub repository malkreide/swiss-public-data-mcp (19 stars, last pushed 1mo ago), licensed MIT. It adds 2,194 tokens to every session, about $0.0088 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.

LLM Python Scientific mcp model-context-protocol open-data swiss-open-data

swiss-public-data-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
swiss-public-data-mcp CLAUDE.mdmalkreide/swiss-public-data-mcp	Instructions file	19	1mo ago	MIT	A	2,194	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

swiss-public-data-mcp: Instructions file for Claude Code