vector_mcp CLAUDE.md

vector_mcp CLAUDE.md is an instructions file for coding agents from sergiobayona/vector_mcp. It costs 4,796 tokens per session, scanned A, a copy of vector_mcp AGENTS.md, MIT.

Repository guidance for VectorMCP, a Ruby library for building Model Context Protocol servers that provide tools and data to language-model clients.

In plain words
What is it for?
Use it when changing VectorMCP code, running its RSpec tests, checking style with RuboCop, or generating YARD documentation.
Why use it?
It gives coding agents the project's setup, testing, linting, and documentation commands so they can work consistently.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/sergiobayona/vector_mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/sergiobayona/vector_mcp

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 vector_mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sergiobayona/vector_mcp/claude-md.svg)](https://agentmods.dev/instructions/sergiobayona/vector_mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sergiobayona/vector_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sergiobayona/vector_mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,796 This file is loaded in full into every session.
When invoked 4,796 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod 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 $0.04796 $0.04796
Opus 5 $0.02398 $0.02398
Sonnet 5 $0.00959 $0.00959
Haiku 4.5 $0.00480 $0.00480

Measured 5d ago against content hash f959a31d7b55, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vector_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 5d 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.

Origin

This is a copy

89% identical to vector_mcp AGENTS.md — 31 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 623 lines

How it starts

The opening of the file, as written. The whole thing — 623 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.

Project Overview

VectorMCP is a Ruby gem implementing the Model Context Protocol (MCP) server-side specification. It provides a framework for creating MCP servers that expose tools, resources, prompts, and roots to LLM clients with comprehensive security features, structured logging, and production-ready capabilities.

Essential Commands

Development Setup

bin/setup          # Install dependencies and setup development environment
bin/console        # Interactive Ruby console with the gem loaded

Testing and Quality

rake               # Run default task (tests + linting)
rake spec          # Run RSpec test suite only
rake rubocop       # Run RuboCop linting only
bundle exec rspec          # Run RSpec test suite  
bundle exec rspec ./spec/vector_mcp/examples_spec.rb # run a single test file
bundle exec rspec ./spec/vector_mcp/logging_spec.rb # run logging tests
bundle exec rubocop       # Run RuboCop linting and style checks

Documentation

rake yard          # Generate YARD documentation
rake doc           # Alias for yard (outputs to doc/ directory)

Example Usage

# Getting Started Examples
ruby examples/getting_started/basic_http_stream_server.rb # MCP-compliant HTTP streaming

# Core Features Examples
ruby examples/core_features/authentication.rb        # Authentication demo
ruby examples/core_features/filesystem_roots.rb      # Filesystem boundaries
ruby examples/core_features/input_validation.rb      # Schema validation
ruby examples/core_features/cli_client.rb           # Command-line client

# Logging Examples
ruby examples/logging/basic_logging.rb              # Component-based logging
ruby examples/logging/structured_logging.rb         # JSON structured output
ruby examples/logging/security_logging.rb           # Security audit logging
ruby examples/logging/log_analysis.rb               # Log processing tools

# Use Cases Examples
ruby examples/use_cases/file_operations.rb          # File system operations
ruby examples/use_cases/data_analysis.rb            # Data processing workflows
ruby examples/use_cases/web_scraping.rb             # Content extraction

# Middleware Examples
ruby examples/middleware_examples.rb                # Comprehensive middleware demo
ruby examples/simple_middleware_demo.rb             # Basic middleware patterns

Read the full file on GitHub · 623 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. 5d ago First seen · 623 lines · 4,796 tokens per session scan A f959a31d7b55

Subscribe to this mod's changes

vector_mcp CLAUDE.md is an instructions file published in the GitHub repository sergiobayona/vector_mcp (13 stars, last pushed 19d ago), licensed MIT. It adds 4,796 tokens to every session, about $0.0240 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to vector_mcp AGENTS.md, differing in 31 lines, and is treated as a copy.