What is codebase-rag-mcp CLAUDE.md?

Repository instructions for an AI coding agent working on omni-rag-mcp, a local tool that searches and analyzes files using both keyword and meaning-based matches.

Understanding the repository, finding code or documents, checking dependencies, and running the MCP server.

They give the agent the project layout, commands, and server-running instructions so it can work in the codebase with the right context.

How Suyash2013/codebase-rag-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Suyash2013/codebase-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/Suyash2013/codebase-rag-mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Suyash2013/codebase-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/suyash2013/codebase-rag-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/suyash2013/codebase-rag-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/suyash2013/codebase-rag-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/suyash2013/codebase-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/suyash2013/codebase-rag-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/suyash2013/codebase-rag-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 731 This file is loaded in full into every session.

When invoked 731 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	$0.00731	$0.00731
Opus 5.5	$0.00292	$0.00292
Sonnet 5.5	$0.00146	$0.00146
Haiku 4.5	$0.00073	$0.00073

Measured 2mo ago against content hash 1cc8b8bb225c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codebase-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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 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 when working with code in this repository.

Project Overview

omni-rag-mcp is a general-purpose RAG MCP plugin for token-efficient semantic search over any directory of files. It auto-ingests the current working directory on first search and provides hybrid search (BM25 + semantic), directory overview, structural analysis, and dependency graphs — all cheaper than repeated file reads.

Zero-config by default: local Qdrant storage, ONNX embeddings, no external services required. Supports code, markdown, PDFs, CSVs, and more via pluggable extractors.

Architecture

MCP Server (mcp_server/): FastMCP server with 8 core tools + deprecated aliases
Extractors (mcp_server/extractors/): Plugin system for content extraction (code, markdown, structured data, PDF, DOCX, image)
Chunkers (mcp_server/chunkers/): Format-aware chunking (code boundaries, markdown headings, CSV rows, etc.)
Storage (mcp_server/storage/): BM25 index + hybrid search rank fusion
Embeddings (mcp_server/embeddings/): Provider abstraction (ONNX, Ollama, OpenAI, Voyage)
Change Detection (mcp_server/change_detection/): Git-based or file-hash-based incremental indexing
Analysis (mcp_server/analysis/): Directory overview and structural analysis
Configuration (config/): Centralized pydantic-settings with OMNI_RAG_ env prefix

Key Commands

# Run the MCP server
omni-rag

# Run tests
python -m pytest tests/ -v

# Health check
python scripts/health_check.py

# Setup (auto-register with Claude Code)
omni-rag-setup

Configuration

All settings via environment variables with OMNI_RAG_ prefix (see config/.env.example):

OMNI_RAG_EMBEDDING_PROVIDER — onnx (default), ollama, openai, voyage
OMNI_RAG_QDRANT_MODE — local (default, zero-config) or remote
OMNI_RAG_INGESTION_TIMEOUT_HOURS — Ingestion timeout (default: 24)
OMNI_RAG_WORKING_DIRECTORY — Override working directory (default: cwd)
OMNI_RAG_HYBRID_SEARCH_ENABLED — Enable BM25+semantic hybrid search (default: true)
OMNI_RAG_ENABLE_CODE_PLUGIN — Enable code-specific tools (default: true)

Read the full file on GitHub · 64 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 · 64 lines · 731 tokens per session scan A 1cc8b8bb225c

Subscribe to this mod's changes

codebase-rag-mcp CLAUDE.md is an instructions file published in the GitHub repository Suyash2013/codebase-rag-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 731 tokens to every session, about $0.0029 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

codebase-rag-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codebase-rag-mcp CLAUDE.mdSuyash2013/codebase-rag-mcp	Instructions file	0	6mo ago	MIT	A	731	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

codebase-rag-mcp: Instructions file for Claude Code