AutoRAG logo

AutoRAG

Search local files and connected sources with hybrid retrieval, cited answers, indexing, and file-organization workflows.

Install AutoRAG

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "autorag": {
      "command": "npx",
      "args": [
        "-y",
        "-p",
        "@autorag/librarian",
        "autorag-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y -p @autorag/librarian autorag-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked .

Overview

AutoRAG MCP server gives coding agents a librarian-style interface for searching files and connected data sources on a computer. It combines keyword and semantic retrieval with reranking, then links answers to the passages used. Reach for it when an agent needs grounded access to local documents, synced cloud folders, messages, mail, code history, or other indexed sources.

Use cases

  • Search project documents by topic or exact phrase
  • Ask questions about indexed files with citations
  • Index selected folders for coding-agent retrieval
  • Search messages, mail, notes, and coding sessions
  • Triage or organize newly added files

Key features

  • Hybrid keyword and semantic retrieval
  • Reranked search results
  • Citations linking answers to source passages
  • Local semantic indexing
  • Folder and connected-source indexing
  • Scheduled re-indexing

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 5h ago via OSV.dev · @autorag/librarian (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars6kStargazers on the source repository.
Last commit1d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.

How AutoRAG works

What AutoRAG does

AutoRAG provides an agent-facing way to search and work with information stored on a computer. Its primary use is finding relevant content inside local files and returning answers tied to the source passages. The wider AutoRAG system also supports file organization workflows, indexing selected folders, duplicate detection, and searches across connected data sources.

The repository distinguishes the newer AutoRAG Agent from the earlier Python AutoRAG project. The newer system is focused on personal knowledge and office-work retrieval; the legacy project remains available under legacy/ for RAG pipeline optimization.

How it works

Search combines traditional keyword matching with meaning-based retrieval and a reranker. This lets an agent find material by exact terms as well as by the subject or idea expressed in a document. Answers can include links to the passages that support them.

Semantic indexing runs locally through MinSync's Qwen3-Embedding-0.6B engine with 1024-dimensional embeddings. File contents are not sent to a remote embedding service unless a remote minSync.embedder is configured. Credentials and API keys are stored in the operating system's encrypted store rather than in a configuration file.

Indexed content can include local documents, synced folders from services such as Google Drive, iCloud Drive, OneDrive, and Dropbox, plus sources including Slack, KakaoTalk, Discord, Telegram, WhatsApp, mail, Notion, GitHub, Obsidian, browser history, RSS, photos, and coding-agent sessions. The available sources depend on the corresponding setup.

Setup and configuration

The project supports agent-assisted setup through the autorag-setup and autorag-lite-setup skills. These workflows ask which folders to index, configure the relevant search setup, and run a health check and test search. The Lite setup is intended to provide model-free search over selected files through an MCP server.

The setup instructions explicitly caution against moving, renaming, editing, or deleting documents during installation. A separate autorag-doctor skill checks the installation and reports per-datasource status.

The repository lists Node.js 24 or newer and Bun 1.2 or newer as supported runtimes. Model access can use the hosted Dazzi Models plan or a provider key supplied by the user.

Tools and capabilities

  • Search indexed files using keyword and semantic matching.
  • Retrieve answers grounded in cited source passages.
  • Index chosen folders and search synced cloud-drive content.
  • Search supported messaging, mail, notes, GitHub, browser, RSS, photo, and coding-session sources.
  • Support file-triage and organization workflows in the broader AutoRAG application.
  • Re-index on a schedule, including while the desktop application is closed.

The repository also includes Dazzi, a desktop application built around the same engine. Dazzi adds file browsing, previews, duplicate grouping, and remote access; these are application features rather than requirements for using the agent-facing search setup.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about AutoRAG

AutoRAG is an MCP server that connects coding agents to indexed local files and supported data sources such as synced drives, messages, mail, notes, and coding sessions. Its main tools and capabilities support folder indexing, hybrid keyword-and-semantic search, reranked retrieval, and answers linked to the source passages behind them.

Install it by following the repository's `autorag-lite-setup` skill, which asks which folders to index, builds the index, registers the MCP server, and verifies it with a real search. The project also provides an `autorag-setup` workflow for the broader AutoRAG librarian system.

Yes, AutoRAG lists Cursor among the coding agents that can be used for setup. Paste the relevant setup instructions into Cursor, then approve the folders to index and complete the model or search configuration it requests.

Yes, semantic indexing runs locally by default through MinSync's Qwen3-Embedding-0.6B engine. File contents are sent to a remote embedder only when a remote `minSync.embedder` is explicitly configured.

AutoRAG lists Node.js 24 or newer and Bun 1.2 or newer. The repository also offers agent-guided setup skills, so installation can be performed through a supported coding agent instead of manually configuring every step.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAutoRAG AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/autorag?style=directory)](https://allmcps.com/mcp/autorag)
HTML Embed
<a href="https://allmcps.com/mcp/autorag"><img src="https://allmcps.com/api/badge/autorag?style=directory" alt="AutoRAG on AllMCPs" /></a>