What is edgar-audit-mcp CLAUDE.md?

A set of project instructions for building and testing an MCP server that provides SEC EDGAR XBRL data. SEC EDGAR is the U.S. Securities and Exchange Commission’s public company-filing database, and XBRL is a structured format used in financial reports.

Use it when changing the edgar-audit-mcp code: read the project guidance, run tests and quality checks, start the server for manual testing, or build its Docker image.

It records project decisions, known mistakes, required checks, and SEC-specific rules so contributors can work consistently and avoid repeating past errors.

How belermirzaa7-ops/edgar-audit-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to belermirzaa7-ops/edgar-audit-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/belermirzaa7-ops/edgar-audit-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/belermirzaa7-ops/edgar-audit-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/belermirzaa7-ops/edgar-audit-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/belermirzaa7-ops/edgar-audit-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/belermirzaa7-ops/edgar-audit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/belermirzaa7-ops/edgar-audit-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/belermirzaa7-ops/edgar-audit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/belermirzaa7-ops/edgar-audit-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42,995 This file is loaded in full into every session.

When invoked 42,995 The same file — it is already loaded in full.

Security scan B 2 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	$0.42995	$0.42995
Opus 5.5	$0.17198	$0.17198
Sonnet 5.5	$0.08599	$0.08599
Haiku 4.5	$0.04299	$0.04299

Measured 1mo ago against content hash 86f67ba42e60, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

edgar-audit-mcp CLAUDE.md scanned grade B with 2 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

2. Bir test temizlik icin `rm -rf` cagiriyordu. Windows'ta boyle bir komut yok.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

1. `subprocess.run(..., text=True)` Windows'ta yerel kod sayfasini kullanir

CLAUDE.md · 2,234 lines

How it starts

The opening of the file, as written. The whole thing — 2,234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — edgar-audit-mcp

Ise baslamadan once PATTERNS.md oku. Bu depoda gercekten yasanmis her hata ve her birinin hangi testle korundugu orada. Bitirmeden once de oradaki kontrol listesinden gec. Bu dosya KARARLARI (neden boyle yapildi) tutar; PATTERNS.md HATALARI (neye dikkat et) tutar.

Bu proje ne

MCP 2026-07-28 spesifikasyonuna uygun, SEC EDGAR XBRL verisini deterministik arac cagrilariyla sunan Python MCP sunucusu.

Komutlar

uv sync --extra dev            # bagimliliklar (pytest/ruff/mypy dahil)
uv run pytest -q               # testler (SEC'e canli cikmaz, HTTP mock'lanir)
uv run mcp dev inspector.py    # MCP Inspector ile elle test (Node.js gerekir)
uv run ruff check . && uv run mypy src
docker build -t edgar-audit-mcp . && docker run --env-file .env -p 8000:8000 edgar-audit-mcp

Kritik mimari kararlar

mcp v2.0.0 kullaniliyor. Giris noktasi MCPServer, FastMCP DEGIL. v1 ornekleri internette hala baskin; from mcp.server.fastmcp import FastMCP yazma, v2'de o modul yok.
Istemci tarafi alan adlari v2'de snake_case: tool.input_schema, tool.output_schema, result.structured_content.
@mcp.tool() orijinal fonksiyonu dondurur; testlerde dogrudan cagrilir.
Her arac Pydantic modeli dondurur -> output_schema otomatik uretilir. Donus tipini dict yapma, sema kaybolur.

SEC kurallari (pazarlik yok)

SEC_USER_AGENT ortam degiskeni zorunlu ve e-posta icermeli; yoksa EdgarClient bilerek hata firlatir.
10 istek/sn ust siniri. RateLimiter 8/sn'de tutuyor, yukseltme.
API anahtari yok, .env'e sadece User-Agent girer.

Repo etigi

.env asla commit edilmez.
stdio transport'ta print() KULLANMA — JSON-RPC akisini bozar. Log stderr'e.
Yeni arac eklerken once testi yaz (HTTP mock'lu), sonra araci.

Dogrulama dongusu

Kod degisikliginden sonra: uv run pytest -q calistir, kirmizi ise duzelt. "Tamamlandi" demeden once testlerin gectigini goster.

Karar kayitlari (neden boyle yapildi)

Read the full file on GitHub · 2,234 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 · +220 lines · +4,634 tokens per session 86f67ba42e60
2mo ago First seen · 2,014 lines · 38,361 tokens per session scan B 12fa6c5fd09b

Subscribe to this mod's changes

edgar-audit-mcp CLAUDE.md is an instructions file published in the GitHub repository belermirzaa7-ops/edgar-audit-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 42,995 tokens to every session, about $0.1720 per session on Opus 5.5. A static security scan graded it B with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Finance and fintech

edgar-audit-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
edgar-audit-mcp CLAUDE.mdbelermirzaa7-ops/edgar-audit-mcp	Instructions file	0	1mo ago	MIT	B	42,995	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

edgar-audit-mcp: Instructions file for Claude Code