tafsir-mcp: Instructions file for Claude Code

CLAUDE.md

tafsir-mcp CLAUDE.md is an instructions file for Claude Code from tafsircenter/tafsir-mcp. It costs 1,237 tokens per session, scanned A, original, MIT.

Project instructions for a server that provides scholarly Quran information, including classical Arabic interpretations, word-level grammar, reading variants, reasons for revelation, and surah statistics. The data is returned from a reviewed database rather than generated.

In plain words
What is it for?
Use it when developing or maintaining the Tafsir MCP server, working with its Arabic Quran database, adding or debugging search and lookup tools, or following its required technology and content rules.
Why use it?
It keeps religious information accurate and traceable by requiring verbatim database content, source attribution, and careful handling of the project’s privacy and technical rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

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

Reuse

Borrowing it

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

agentmods badge for tafsir-mcp CLAUDE.md

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

agentmods 80×15 button for tafsir-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tafsircenter/tafsir-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tafsircenter/tafsir-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,237 This file is loaded in full into every session.
When invoked 1,237 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 $0.01237 $0.01237
Opus 5.5 $0.00495 $0.00495
Sonnet 5.5 $0.00247 $0.00247
Haiku 4.5 $0.00124 $0.00124

Measured 2mo ago against content hash 7ea2295d6948, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tafsir-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 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tafsir MCP Server

📍 اقرأ STATE.md (في الجذر) أولًا للحالة الحيّة (الإصدار المنشور، الصورة، العمل الجاري). هذا الملف للقواعد والعادات الثابتة.

Project Overview

MCP server providing scholarly, certified access to the Quran with 5 classical Arabic tafsirs (Tabari, Ibn Kathir, Baghawi, Saadi, Muyassar), word-level grammatical analysis (i'rab, sarf, root), qira'at variants, asbab al-nuzool, and surah statistics. Sponsored by Tafsir Center for Quranic Studies (https://tafsir.net). Religious content — accuracy is paramount.

Sponsoring Organization

This project is sponsored by Tafsir Center for Quranic Studies (مركز تفسير للدراسات القرآنية, https://tafsir.net). The Quranic database is reviewed and certified by the Center's scholars.

Tech Stack

  • Python 3.12 with FastMCP (mcp[cli] >= 1.27.0)
  • SQLite 3 + FTS5 for full-text search
  • Pydantic v2 for input validation (strict mode)
  • pyarabic for Arabic text normalization

Critical Rules (NEVER VIOLATE)

  1. No content generation. Tools return data verbatim from the database. Never summarize, paraphrase, or "improve" religious text.
  2. Always attribute. Every tafsir response includes a source field with author name, book title, death year.
  3. Strict input validation. Every tool parameter uses Pydantic Field with constraints (e.g., surah: int = Field(ge=1, le=114)).
  4. Parametrized SQL only. Use ? placeholders. Never f-string SQL.
  5. All Quranic ayah counts MUST validate against 6236 total ayahs and 114 surahs.

FastMCP Parameter Pattern (Critical Bug Avoidance)

NEVER write param: int = Field(ge=1, le=114, default=1) in tool/prompt functions. The Field() object becomes the default value (FieldInfo) instead of the integer — silent bug.

ALWAYS use Annotated with a separate Python default:

# ✅ CORRECT
from typing import Annotated
param: Annotated[int, Field(ge=1, le=114)] = 1

# ❌ WRONG — passes FieldInfo to SQLite, causes ProgrammingError
param: int = Field(ge=1, le=114, default=1)

Required params (no default): param: Annotated[int, Field(ge=1, le=114)] — no = value.

Read the full file on GitHub · 90 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 · 90 lines · 1,237 tokens per session scan A 7ea2295d6948

Subscribe to this mod's changes

tafsir-mcp CLAUDE.md is an instructions file published in the GitHub repository tafsircenter/tafsir-mcp (75 stars, last pushed 5mo ago), licensed MIT. It adds 1,237 tokens to every session, about $0.0049 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 2026-08-30.

Related

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

tafsir-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tafsir-mcp CLAUDE.mdtafsircenter/tafsir-mcpInstructions file755mo agoMITA1,237Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot