What is claude-rag-mcp CLAUDE.md?

Instructions for a Claude Code project that provides RAG context and stores coding failures. RAG means retrieving relevant saved information to give an agent useful context later.

Use them when developing or maintaining the project, especially its context search and storage features or its records of tests, reviews, quality checks, timeouts and errors.

They document the project's architecture, available MCP commands and technical stack, making the repository easier to work on consistently.

How VXConsulting/claude-rag-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to VXConsulting/claude-rag-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/VXConsulting/claude-rag-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/VXConsulting/claude-rag-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/vxconsulting/claude-rag-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/vxconsulting/claude-rag-mcp/claude-md)

Your own site

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

Per session 602 This file is loaded in full into every session.

When invoked 602 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.

Model	Per session	Once invoked
Fable 5.1	$0.00602	$0.00602
Opus 5.5	$0.00241	$0.00241
Sonnet 5.5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 2mo ago against content hash 082ded700b14, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-rag-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 · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Last Updated: 2026-02-02 (v1.0.0 - Initial Release)

Project Overview

Repository: /home/olivier/dev/claude-rag-mcp Branch: main Version: 1.0.0 Purpose: MCP server providing RAG context and failure capture for Claude Code

Architecture

MCP Server (src/mcp/server.ts)
  ↓
┌─────────────────────────────────────────────────────┐
│ Context (RAG)                                        │
│   src/context/ - semantic search, knowledge store   │
│   Providers: memory, chromadb                       │
└─────────────────────────────────────────────────────┘
  ↓
┌─────────────────────────────────────────────────────┐
│ Learning (Capture)                                   │
│   src/learning/ - failure storage (SQLite)          │
│   Types: test, review, quality_gate, timeout, error │
└─────────────────────────────────────────────────────┘

MCP Tools (11 total)

Context (7): context_status, context_search, context_list, context_get, context_add, context_delete, context_prune
Learning (4): learning_status, learning_list_failures, learning_get_failure, learning_prune

Technical Stack

Language: TypeScript 5.7 (strict mode) with NodeNext module resolution
Module System: ESM ("type": "module")
Testing: Vitest 4.0 with colocated __tests__/ directories
MCP: @modelcontextprotocol/sdk 1.0

Key Files

src/mcp/server.ts - MCP server with 11 tools
src/mcp/context-tools.ts - 7 RAG tools
src/mcp/learning-tools.ts - 4 failure capture tools
src/context/ - Global context module (RAG system)
src/learning/ - Failure capture service
src/cli.ts - CLI entry point (serve command)
src/config/config-loader.ts - YAML config loader

Commands

npm run build          # Compile TypeScript
npm test               # Run all tests
npm run test:watch     # Watch mode
npm run serve          # Start MCP server

Conventions

ESM with NodeNext module resolution
Strict TypeScript throughout
Tests colocated in __tests__/ directories
Use import { randomUUID } from 'node:crypto' (Node 18+)
Zod for config validation with safeParse

Read the full file on GitHub · 72 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.

2mo ago First seen · 72 lines · 602 tokens per session scan A 082ded700b14

Subscribe to this mod's changes

claude-rag-mcp CLAUDE.md is an instructions file published in the GitHub repository VXConsulting/claude-rag-mcp (1 stars, last pushed 9mo ago), licensed MIT. It adds 602 tokens to every session, about $0.0024 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.

Data and AI RAG and vectors

claude-rag-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-rag-mcp CLAUDE.mdVXConsulting/claude-rag-mcp	Instructions file	1	9mo ago	MIT	A	602	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

claude-rag-mcp: Instructions file for Claude Code