What is pluggy-mcp-server CLAUDE.md?

Project instructions for a read-only MCP server that exposes one person's Brazilian bank, credit-card, and investment data through Pluggy, a Brazilian Open Finance service. It cannot move money.

Reading and reconciling personal financial data, following the project's amount and language rules, and choosing between its two server registrations.

They help agents handle financial data consistently, calculate totals with code, and avoid unsafe operations or incorrect currency interpretations.

How brunopedrazza/pluggy-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to brunopedrazza/pluggy-mcp-server. 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/brunopedrazza/pluggy-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/brunopedrazza/pluggy-mcp-server

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/brunopedrazza/pluggy-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/brunopedrazza/pluggy-mcp-server/claude-md)

Your own site

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

Per session 837 This file is loaded in full into every session.

When invoked 837 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	$0.00837	$0.00837
Opus 5.5	$0.00335	$0.00335
Sonnet 5.5	$0.00167	$0.00167
Haiku 4.5	$0.00084	$0.00084

Measured 2mo ago against content hash 2c839edc7299, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pluggy-mcp-server 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 · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — pluggy-mcp-server

Guidance for any agent working in this repo. Read DESIGN.md first — every decision and its reasoning lives there, and README.md covers setup and deployment.

What this is

A read-only MCP server over one person's real bank, credit card and investment data (Brazilian Open Finance, via Pluggy). It cannot move money, and a test fails if anyone imports Pluggy's PaymentsClient. Keep it that way.

Hard conventions

English only in repo artifacts: code, comments, docs, commit messages. (Conversations with the owner happen in Portuguese; nothing Portuguese lands in the repo.)
Never sum rows mentally. Write and run code. A month is hundreds of rows and a quietly wrong total is worse than no answer — the same rule the server injects into its own handshake.
Amounts are normalised so negative always means money leaving the account, on bank accounts and cards alike, and always in the account's own currency. valor_orig is for reconciliation only: never sum it, never read it as reais.

Two MCP registrations, and which one to use

Once the server is deployed (README) you have two of it: the one on the VM, and whatever npm run dev is serving out of your working tree. Register them as separate entries — the deployed one globally, the local one scoped to this directory — so the split is decided by where you are rather than by guesswork:

server	points at	use it for
`pluggy`	the VM, running `origin/main`	any real question about the owner's finances
`pluggy-dev`	`127.0.0.1:8787`, this working tree	exercising a change you are making right now

pluggy-dev only answers while npm run dev is running, so a ConnectionRefused from it means the dev server is down, not that anything is broken.

They read the same account with the same credentials, so the numbers are not "test data" — they are the real numbers, computed by whichever code you happen to be pointing at. Picking pluggy-dev by accident does not produce an obvious error; it produces a plausible figure from a half-finished edit. So: pluggy-dev only to verify your own change behaves, pluggy for anything whose answer the owner might act on.

Read the full file on GitHub · 70 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 First seen · 70 lines · 837 tokens per session scan A 2c839edc7299

Subscribe to this mod's changes

pluggy-mcp-server CLAUDE.md is an instructions file published in the GitHub repository brunopedrazza/pluggy-mcp-server (4 stars, last pushed 2mo ago), licensed MIT. It adds 837 tokens to every session, about $0.0033 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.

Finance and fintech

pluggy-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pluggy-mcp-server CLAUDE.mdbrunopedrazza/pluggy-mcp-server	Instructions file	4	2mo ago	MIT	A	837	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
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	today	MIT	A	4,335	Codex, OpenCode

pluggy-mcp-server: Instructions file for Claude Code