What is mcp-rag-server CLAUDE.md?

Project instructions for a Python MCP server that uses retrieval-augmented generation, a way to search indexed documents and use the results in answers. The instructions cover setup, commands, testing, formatting, and pull requests.

Setting up the project with uv and PostgreSQL with pgvector; indexing or clearing documents; checking document counts; running tests and Ruff; and preparing pull requests.

They explain how to install dependencies, prepare the database, run the server, manage the document index, and follow the repository's development rules.

mcp-rag-server CLAUDE.md — Instructions file for Claude Code by FORIFOR: Project instructions for a Python MCP server that uses…

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/forifor/mcp-rag-server/claude-md

Clone the repo

git clone --depth 1 https://github.com/FORIFOR/mcp-rag-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/forifor/mcp-rag-server/claude-md.svg)](https://agentmods.dev/instructions/forifor/mcp-rag-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/forifor/mcp-rag-server/claude-md"><img src="https://agentmods.dev/badge/instructions/forifor/mcp-rag-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,274 This file is loaded in full into every session.

When invoked 1,274 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin 100% 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.

Model	Per session	Once invoked
Fable 5.1	$0.01274	$0.01274
Opus 5	$0.00637	$0.00637
Sonnet 5	$0.00255	$0.00255
Haiku 4.5	$0.00127	$0.00127

Measured 5d ago against content hash e5d4ac6b167d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-rag-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 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

100% identical to mcp-rag-server CLAUDE.md — 0 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 · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 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.

プロジェクト概要

MCP RAG Serverは、Model Context Protocol (MCP)とRAG (Retrieval-Augmented Generation)機能を実装したPythonサーバーです。複数のドキュメント形式に対応したベクトル検索システムを提供します。

主要コマンド

開発環境セットアップ

# 依存関係のインストール (uvを使用)
uv sync

# PostgreSQLとpgvectorのセットアップが必要
# DockerでPostgreSQLを起動:
docker run -d \
  --name pgvector-db \
  -e POSTGRES_USER=your_user \
  -e POSTGRES_PASSWORD=your_password \
  -e POSTGRES_DB=your_database \
  -p 5432:5432 \
  pgvector/pgvector:pg16

# .envファイルの設定が必要

実行コマンド

# MCPサーバーの起動
uv run python -m src.main

# CLIでドキュメントをインデックス
uv run python -m src.cli index
uv run python -m src.cli index --incremental  # 差分インデックス

# インデックスのクリア
uv run python -m src.cli clear

# ドキュメント数の確認
uv run python -m src.cli count

テスト実行

# pytestでテスト実行
uv run pytest

Lint・フォーマット

# ruffでlintチェック
uv run ruff check --line-length=127

# ruffで自動フォーマット
uv run ruff format --line-length=127

# フォーマットチェック（差分表示）
uv run ruff format --check --diff --line-length=127

Pull Request(PR)

PR作成時

PRを要望されたら、gitコマンドで差分を確認したうえで、gh pr コマンドを使ってPRを作成してください
PRのdescriptionは .github/pull_request_template.md を読み取ってフォーマットを合わせてください

PRレビュー時

以下の手順でファイルごとにコメントを付けてください：

チェックする観点は .github/pull_request_template.md を参照してください
PRの差分を確認:
```
gh pr diff <PR番号>
```
ファイルごとに、変更後のファイル全体とPRの差分を確認した上でレビューコメントを追加:
```
gh api repos/<owner>/<repo>/pulls/<PR番号>/comments \
  -F body="レビューコメント" \
  -F commit_id="$(gh pr view <PR番号> --json headRefOid --jq .headRefOid)" \
  -F path="対象ファイルのパス" \
  -F position=<diffの行番号>
```
パラメータの説明：
- position: diffの行番号（新規ファイルの場合は1から開始）
- commit_id: PRの最新のコミットIDを自動取得

アーキテクチャ概要

コア構成

MCPサーバー層: src/mcp_server.pyがJSON-RPC通信を処理
RAGサービス層: src/rag_service.pyがドキュメント処理と検索を統括
データ層: PostgreSQL + pgvectorでベクトルデータベースを実装

主要モジュール

src/main.py: エントリーポイント
src/rag_tools.py: MCP用の検索ツール定義
src/document_processor.py: ドキュメント解析とチャンク化
src/embedding_generator.py: multilingual-e5-largeモデルでの埋め込み生成
src/vector_database.py: PostgreSQL/pgvectorインターフェース

Read the full file on GitHub · 143 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.

5d ago First seen · 143 lines · 1,274 tokens per session scan A e5d4ac6b167d

Subscribe to this mod's changes

mcp-rag-server CLAUDE.md is an instructions file published in the GitHub repository FORIFOR/mcp-rag-server (0 stars, last pushed 7mo ago), licensed MIT. It adds 1,274 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mcp-rag-server CLAUDE.md, differing in 0 lines, and is treated as a copy.

Data and AI RAG and vectors

GPT-RAG release.instructions.md

Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

Azure/GPT-RAG · 207 tokens

gpt-rag-ingestion api-frontend.instructions.md

Instructions for Azure/gpt-rag-ingestion, a project described as: The GPT-RAG Data Ingestion service automates processing of diverse documents—PDFs, images, spreadsheets, transcripts, and SharePoint—readying them for Azure AI Search. It applies smart chunking, generates text and image embeddings, and enables rich…

Azure/gpt-rag-ingestion · 208 tokens

mcp-rag-server CLAUDE.md