ruby_mcp_server: Instructions file for Claude Code

CLAUDE.md

ruby_mcp_server CLAUDE.md is an instructions file for Claude Code from ajentik/ruby_mcp_server. It costs 484 tokens per session, scanned A, original, MIT.

Repository instructions for a Ruby gem that provides a configurable web server using Rack and the Model Context Protocol, a standard way for applications to expose tools to AI systems.

In plain words
What is it for?
It is for running the test suite, checking Ruby style, building the gem, installing it locally, and understanding its main server components.
Why use it?
It keeps development work consistent by documenting the project structure and the commands for testing, linting, building, and local installation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is ajentik/ruby_mcp_server's own configuration. It tells Claude Code how to work on ruby_mcp_server 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 ruby_mcp_server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ajentik/ruby_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/ajentik/ruby_mcp_server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ajentik/ruby_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.

agentmods badge for ruby_mcp_server CLAUDE.md

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

agentmods 80×15 button for ruby_mcp_server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ajentik/ruby_mcp_server/claude-md"><img src="https://agentmods.dev/badge/instructions/ajentik/ruby_mcp_server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 484 This file is loaded in full into every session.
When invoked 484 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 $0.00484 $0.00484
Opus 5.5 $0.00194 $0.00194
Sonnet 5.5 $0.00097 $0.00097
Haiku 4.5 $0.00048 $0.00048

Measured 2mo ago against content hash 30756dd1e3a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ruby_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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

This is a Ruby gem called mcp_server that provides a configurable Rack-based MCP (Model-Context-Protocol) server. It's designed to be pluggable and protocol-agnostic, allowing developers to integrate MCP functionality into their Rack-based applications.

Common Commands

Testing

# Run all tests
bundle exec rake test
# or simply
bundle exec rake

# Run a specific test file
ruby -Ilib:test test/test_configuration.rb

Linting

# Run StandardRB for Ruby style checking
standardrb

Building the Gem

# Build the gem
gem build mcp_server.gemspec

# Install locally for testing
gem install ./mcp_server-0.1.0.gem

Architecture

Core Components

  1. MCP Server Configuration (lib/mcp_server/configuration.rb): Central configuration object that stores callbacks for authentication, user resolution, and tool resolution. Uses a DSL pattern for easy setup.

  2. Rack Application (lib/mcp_server/rack_app.rb): The main entry point for HTTP requests. Implements the request/response cycle:

    • Authenticates requests using the configured callback
    • Resolves users and tools
    • Returns JSON responses

Key Design Patterns

  • Callback-based Configuration: The gem uses callbacks (procs) for authentication and resolution logic, allowing users to plug in their own implementations
  • Rack Middleware Pattern: Built as a Rack application, making it compatible with any Ruby web framework
  • Dependency Injection: Callbacks are injected through configuration

Integration Points

When integrating this gem:

  1. Configure authentication logic via MCPServer.configure { |c| c.authenticate_with { |request| ... } }
  2. Set up user and tool resolution callbacks
  3. Mount the Rack app in your application (e.g., in Rails routes or config.ru)

Testing Approach

The gem uses Minitest with rack/mock for simulating HTTP requests. Tests are organized by component and focus on configuration behavior.

Read the full file on GitHub · 63 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 · 63 lines · 484 tokens per session scan A 30756dd1e3a8

Subscribe to this mod's changes

ruby_mcp_server CLAUDE.md is an instructions file published in the GitHub repository ajentik/ruby_mcp_server (4 stars, last pushed 4d ago), licensed MIT. It adds 484 tokens to every session, about $0.0019 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.

Related

ruby_mcp_server CLAUDE.md compared with instructions from other repositories

ruby_mcp_server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ruby_mcp_server CLAUDE.mdajentik/ruby_mcp_serverInstructions file44d agoMITA484Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file281kyesterdayMITA4,335Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot