What is pp-mcp CLAUDE.md?

Repository guidance for pp-mcp, a read-only server that supplies account and investment-portfolio data from Portfolio Performance files. MCP is a standard way for AI tools to call an external server.

Use it when developing, documenting, deploying, or connecting tools to the pp-mcp server and its Portfolio Performance data.

It defines how portfolio data should be accessed and protected, so other applications do not parse the files independently. It also records the project’s language and operating conventions.

How Nokke32/pp-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Nokke32/pp-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/Nokke32/pp-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Nokke32/pp-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/nokke32/pp-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nokke32/pp-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nokke32/pp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nokke32/pp-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/nokke32/pp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/nokke32/pp-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,258 This file is loaded in full into every session.

When invoked 3,258 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	$0.03258	$0.03258
Opus 5.5	$0.01303	$0.01303
Sonnet 5.5	$0.00652	$0.00652
Haiku 4.5	$0.00326	$0.00326

Measured 3d ago against content hash 0f7872197de4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pp-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 3d 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 · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Hinweise für Claude Code beim Arbeiten in diesem Repository.

Überblick

pp-mcp ist ein read-only MCP-Server, der Konten- und Depotdaten aus einer oder mehreren Portfolio-Performance-.portfolio-Dateien gefiltert bereitstellt (für Reports). Ein einzelner Python-Prozess, nur MCP – keine Web-UI, keine Datenbank, keine Auth (außer optionalem Bearer-Token). Tool-Beschreibungen, Docstrings und Kommentare in src/mcp_server.py sind auf Englisch (öffentlicher MCP-Server, internationale Nutzer/ LLMs). Diese CLAUDE.md und Commit-Messages bleiben auf Deutsch (Arbeitssprache des Maintainers).

pp-mcp ist als einzige Quelle der Wahrheit für Portfolio-Performance-Daten gedacht: andere Anwendungen (z.B. DividendenTracker, ein künftiges Analyse-Dashboard) sollen ausschließlich über diesen Server auf .portfolio-Dateien zugreifen und sie nicht selbst parsen. Produktivbetrieb: NAS im lokalen Netz, intern im Docker-Netz (nicht öffentlich exponiert, außer über einen Reverse-Proxy unter einer festen internen Domain), zusätzlich per MCP_AUTH_TOKEN geschützt.

Dokumentation: Seit 2026-08-14 ist die ausführliche Doku (Installation, KI-Tool-Konfiguration, Beispiel-Prompts, vollständige Tool-Referenz, Beispiel-Skripte) im Wiki, nicht mehr in der README. Zwei gespiegelte Wikis: Gitea (primäre Quelle, intern gehostet, lokaler Klon unter ~/Coding/MCP/pp-mcp.wiki) und GitHub (https://github.com/Nokke32/pp-mcp/wiki, Branch master statt main). README.md/ README_de.md sind auf ein Minimum reduziert (Kurzbeschreibung, Quick-Start, Begriffe, Struktur) und verlinken je nach Remote auf das jeweils passende Wiki (Gitea ist nur intern erreichbar, daher zwei unterschiedliche Link-Ziele in den sonst identischen READMEs).

Betrieb & Entwicklung

Gedacht für Docker, läuft aber auch lokal. docker-compose.yml ist der Multi-Source-Produktivbetrieb (NAS im lokalen Netz, MCP_AUTH_TOKEN Pflicht); docker-compose.dev.yml der einfache lokale Single-Source-Betrieb (docker-compose -f docker-compose.dev.yml up -d --build):

Read the full file on GitHub · 171 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.

3d ago Changed · +16 lines · +373 tokens per session 0f7872197de4
2mo ago First seen · 155 lines · 2,885 tokens per session scan A fc0ec9dddf27

Subscribe to this mod's changes

pp-mcp CLAUDE.md is an instructions file published in the GitHub repository Nokke32/pp-mcp (10 stars, last pushed 4d ago), licensed MIT. It adds 3,258 tokens to every session, about $0.0130 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.

pp-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pp-mcp CLAUDE.mdNokke32/pp-mcp	Instructions file	10	4d ago	MIT	A	3,258	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	3,086	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

pp-mcp: Instructions file for Claude Code