What is local-rag-mcp CLAUDE.md?

Project instructions for a local retrieval-augmented generation (RAG) server. RAG searches a stored knowledge base and supplies relevant results to an application; this project uses FastMCP, LanceDB, and combined keyword and meaning-based search.

Use it when developing, testing, packaging, or modifying the local RAG MCP server, including its document parsers, search engine, database storage, and MCP tools.

It gives a coding agent the project’s layout, commands, architecture, and data-processing pipeline so work follows the repository’s existing conventions.

How junchenghe01/local-rag-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to junchenghe01/local-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/junchenghe01/local-rag-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/junchenghe01/local-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/junchenghe01/local-rag-mcp/claude-md.svg)](https://agentmods.dev/instructions/junchenghe01/local-rag-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/junchenghe01/local-rag-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/junchenghe01/local-rag-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 818 This file is loaded in full into every session.

When invoked 818 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	$0.00818	$0.00818
Opus 5	$0.00409	$0.00409
Sonnet 5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 7d ago against content hash 783fb183a093, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

local-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 7d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 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

RAG Knowledge MCP Server — FastMCP + LanceDB + Hybrid Search, full MCP 5 features (Tools/Resources/Prompts/Sampling/Roots).

Commands

.\.venv\Scripts\python.exe -m src.local_rag_mcp.server        # 开发模式启动
.\.venv\Scripts\python.exe -m pip install -e .                 # 可编辑安装
.\.venv\Scripts\python.exe -m build                            # 构建 sdist + wheel (dist/)
.\.venv\Scripts\python.exe -m pytest tests/ -v                 # 运行测试

Architecture

src/local_rag_mcp/
├── __init__.py       # Package marker
├── server.py         # FastMCP entry — 7 tools + 2 resources + 1 prompt + Sampling + Roots
├── engine.py         # Core: EmbeddingClient, HybridSearchEngine, IngestionPipeline
├── lancedb_store.py  # LanceDB storage layer (IVF-PQ + BM25 FTS)
├── chunker.py        # Smart chunking (600char/60overlap, sentence boundary)
├── parsers/          # Multi-modal ETL parsers
│   ├── __init__.py
│   ├── pdf_parser.py     # PyPDF paragraph reconstruction
│   ├── word_parser.py    # python-docx object tree traversal
│   ├── excel_parser.py   # pandas matrix serialization (20 rows/section)
│   └── text_parser.py    # MD/TXT/HTML text extraction
├── watcher.py        # Watchdog file monitoring + 1.0s debounce
├── sampling.py       # Sampling callback for noisy document cleaning
├── logger.py         # Loguru-based structured logging (daily rotation)
└── status.py         # Thread-safe server status tracking

tests/                  # Test suite (80 tests)

RAG Pipeline (v2.1)

Document Parsing: Custom parsers (PyPDF/python-docx/pandas) extract text
Smart Chunking: 600 char chunks, 60 char overlap, sentence boundary detection
Embedding: Direct Ollama /api/embeddings call, auto-detect dimension
Storage: LanceDB embedded vector DB with IVF-PQ dense index + BM25 FTS
Search: Hybrid ANN + BM25 dual recall, RRF (Reciprocal Rank Fusion) merge
File Watch: Watchdog monitors file changes, auto re-index with 1.0s debounce

Read the full file on GitHub · 75 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.

7d ago First seen · 75 lines · 818 tokens per session scan A 783fb183a093

Subscribe to this mod's changes

local-rag-mcp CLAUDE.md is an instructions file published in the GitHub repository junchenghe01/local-rag-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 818 tokens to every session, about $0.0041 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.

Data and AI RAG and vectors

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

local-rag-mcp: Instructions file for Claude Code