Borrowing it
Nothing to install: this file belongs to woodstocksoftware/question-bank-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.
curl -O https://raw.githubusercontent.com/woodstocksoftware/question-bank-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/woodstocksoftware/question-bank-mcpWrote 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.
[](https://agentmods.dev/instructions/woodstocksoftware/question-bank-mcp/claude-md)<a href="https://agentmods.dev/instructions/woodstocksoftware/question-bank-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/woodstocksoftware/question-bank-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.
<a href="https://agentmods.dev/instructions/woodstocksoftware/question-bank-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/woodstocksoftware/question-bank-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01362 | $0.01362 |
| Opus 5 | $0.00681 | $0.00681 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
question-bank-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Question Bank MCP Server
Tech Stack
- Language: Python 3.12
- Framework: FastMCP (
mcp>=1.0.0) - Database: SQLite (auto-created at
data/question_bank.db) - Transport: stdio
- Testing: pytest + pytest-cov (88 tests, 93% coverage)
- Dependencies:
mcp>=1.0.0,python-dateutil>=2.8.0,pytest>=9.0.0,pytest-cov>=7.0.0
How to Run
# From project root (with venv activated)
python run_server.py
# Or as a module
python -m src.question_bank
How to Connect
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"question-bank": {
"command": "/path/to/question-bank-mcp/venv/bin/python",
"args": ["/path/to/question-bank-mcp/run_server.py"]
}
}
}
Claude Code
claude mcp add question-bank /path/to/question-bank-mcp/venv/bin/python /path/to/question-bank-mcp/run_server.py
Architecture
run_server.py # Entry point — imports mcp from server.py, runs stdio
src/question_bank/
├── __init__.py
├── __main__.py # python -m entry point
├── server.py # 12 MCP tools + 2 MCP resources (~800 lines)
└── database.py # SQLite ORM layer (~500 lines)
tests/
├── conftest.py # DB isolation fixture (tmp_path per test)
├── test_database.py # 40 tests — CRUD, search, cascades, security
└── test_server.py # 48 tests — validation, tools, formatting
data/
└── question_bank.db # SQLite database (auto-created, gitignored)
server.pydefines all tools and resources using the@mcp.tool()and@mcp.resource()decoratorsdatabase.pyhandles all SQL — table creation, CRUD, search queries- The database auto-initializes on first import (creates tables + indexes)
Tools (12)
| Tool | Key Parameters |
|---|---|
create_question_bank |
name, subject, description?, grade_level? |
list_question_banks |
(none) |
get_bank_statistics |
bank_id |
create_topic |
bank_id, name, description?, parent_topic_id? |
list_topics |
bank_id |
create_question |
bank_id, question_type, stem, correct_answer, options?, explanation?, difficulty?, bloom_level?, estimated_time_seconds?, points?, topic_ids?, tags? |
get_question |
question_id, show_answer? |
update_question |
question_id, plus any question field |
delete_question |
question_id |
search_questions |
bank_id?, topic_id?, question_type?, bloom_level?, difficulty_min?, difficulty_max?, status?, tags?, search_text?, limit? |
activate_questions |
question_ids (list) |
suggest_questions |
bank_id, topic, count?, difficulty?, bloom_levels? |
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.
- 10d ago First seen · 140 lines · 1,362 tokens per session scan A 42a05db6a6e9
question-bank-mcp CLAUDE.md is an instructions file published in the GitHub repository woodstocksoftware/question-bank-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,362 tokens to every session, about $0.0068 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.