DevRagSAFE
Markdown vector search MCP server for Claude Code. Natural language search for markdown files using multilingual-e5-small embeddings.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Free Local RAG for Claude Code - Save Tokens & Time
日本語版はこちら | Japanese Version
DevRag is a lightweight RAG (Retrieval-Augmented Generation) system designed specifically for developers using Claude Code. Stop wasting tokens by reading entire documents - let vector search find exactly what you need.
Why DevRag?
When using Claude Code, reading documents with the Read tool consumes massive amounts of tokens:
- ❌ Wasting Context: Reading entire docs every time (3,000+ tokens per file)
- ❌ Poor Searchability: Claude doesn't know which file contains what
- ❌ Repetitive: Same documents read multiple times across sessions
With DevRag:
- ✅ 40x Less Tokens: Vector search retrieves only relevant chunks (~200 tokens)
- ✅ 15x Faster: Search in 100ms vs 30 seconds of reading
- ✅ Auto-Discovery: Claude Code finds documents without knowing file names
Features
- 🤖 Simple RAG - Retrieval-Augmented Generation for Claude Code
- 📝 Markdown Support - Auto-indexes .md files
- 🔍 Semantic Search - Natural language queries like "JWT authentication method"
- 🚀 Single Binary - No Python, models auto-download on first run
- 💻 CLI & MCP - Use as MCP server or standalone CLI commands
- 🖥️ Cross-Platform - macOS / Linux / Windows
- ⚡ Fast - Auto GPU/CPU detection, incremental sync
- 🌐 Multilingual - Supports 100+ languages including Japanese & English
Quick Start
1. Download Binary
Get the appropriate binary from Releases:
macOS/Linux:
tar -xzf devrag-*.tar.gz chmod +x devrag-* sudo mv devrag-* /usr/local/bin/
Note: macOS
28173479f878OBSERVED · 2026-10-07Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
.mcp.json.example
.keep
Gates applied: no_behavioural_pass, no_license.
28173479f878full audit observations/trust-audit/mcp-server/tomohiro-owada__devrag.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 28173479f878 | SAFE | B | 89 | first audit |
Questions
What is the DevRag MCP server?
Markdown vector search MCP server for Claude Code. Natural language search for markdown files using multilingual-e5-small embeddings.
Is DevRag safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does DevRag need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (28173479f878), read on 2026-10-07. The repository is watched and re-audited when it changes.