MiniRAG

io.github.KiMelodyPublished by GitHub account KiMelodyv0.1.0Updated Oct 30, 2026

Lightweight self-hosted RAG knowledge base with hybrid retrieval and cited answers.

VerifiedSSEWeb executableDatabases Knowledge & Memory

Server details

Identifier: io.github.KiMelody/minirag
Transport: SSE
Runtime: Web executable
Trust: Verified
Published: Oct 15, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account KiMelody for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.KiMelody%2Fminirag.svg)](https://sourceweft.com/mcp/io.github.KiMelody%2Fminirag?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

MiniRAG is a self-hosted RAG knowledge base whose MCP server lets an assistant ask cited questions over your own documents and add new text.

What you can do: Ask questions against the knowledge base and get answers with numbered citations, choosing vector, hybrid or rerank retrieval mode
Add documents to the knowledge base as text, which requires the admin key
Retrieval is hybrid: in-memory cosine similarity plus SQLite FTS5 BM25 fused with RRF, with optional LLM reranking
Beyond MCP, the same process exposes a REST API, a streaming web UI and a WeChat Work callback
When to use it: Useful when you want an assistant to answer from a private document collection you control, with citations back to the sources, and to add new material to that collection as you go. Suited to small self-hosted deployments rather than large-scale search infrastructure.
Requirements: The hosted endpoint is a remote SSE URL that requires HTTP Basic auth in the Authorization header, with credentials obtained from the owner. Self-hosting needs Docker or Java 21, plus a chat model API key and an embeddings API key (OpenAI-compatible endpoints, configurable base URLs and embedding model).

Before you install

The hosted demo is gated by a shared access code from the owner, so treat it as a public demo rather than private storage. Ingesting documents requires the admin key and writes data into the knowledge base. Questions and ingested text are sent to the configured external chat and embedding providers, so avoid confidential material unless you self-host with providers you trust.

Installation

In SourceWeft

Open MiniRAG in the dashboard and add it to a workspace.
Connect Authorization token credentials. They are stored privately and never shown on public pages.
Enable the server for the chats that should use its tools.

Web executable via SSE. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.KiMelody%2Fminirag/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "minirag": {
      "type": "sse",
      "url": "https://minirag.kimelody.de5.net/sse",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

MiniRAG

[Build] [License: MIT] [Java] [RSS]

A self-hosted RAG knowledge base in a single Spring Boot process: SQLite storage, hybrid retrieval, cited answers, and a built-in MCP server. No vector database, no message queue.

Live demo (ask the owner for the access code) · Evaluation report

Features

Hybrid retrieval — in-memory cosine + SQLite FTS5 (BM25), fused with RRF; optional LLM rerank
Cited answers — clickable [n] citations; only sources actually cited are displayed
Streaming web UI — SSE, typewriter rendering, markdown, retrieval-mode switcher (vector / hybrid / rerank)
Small footprint — single process, ~250MB RSS, runs on a 1GB VPS
Multiple interfaces — MCP server (SSE transport), REST API, web UI, WeChat Work callback integration

Quick start

bash

docker run -d --name minirag -p 18090:18090 --memory 512m \  -v $(pwd)/data:/app/data \  -e DEEPSEEK_API_KEY=sk-... \  -e EMBEDDING_API_KEY=sk-... \  ghcr.io/kimelody/minirag:latest

docker run -d --name minirag -p 18090:18090 --memory 512m \  -v $(pwd)/data:/app/data \  -e DEEPSEEK_API_KEY=sk-... \  -e EMBEDDING_API_KEY=sk-... \  ghcr.io/kimelody/minirag:latest

Open http://localhost:18090 and start asking. Data lives in ./data (SQLite, created automatically).

Configuration

Env	Required	Default	Description
`DEEPSEEK_BASE_URL`	no	`https://api.deepseek.com`	Any OpenAI-compatible chat endpoint
`DEEPSEEK_API_KEY`	yes	—	Chat model API key
`EMBEDDING_BASE_URL`	no	`https://api.siliconflow.cn/v1`	OpenAI-compatible embeddings endpoint
`EMBEDDING_API_KEY`	yes	—	Embeddings API key
`EMBEDDING_MODEL`	no	`BAAI/bge-m3`	Embedding model
`DEMO_KEY`	no	—	Visitor access code for read APIs; unset = open (local dev)
`ADMIN_KEY`	no	—	Admin key required for ingest APIs

MCP

Listed on the official MCP Registry as io.github.KiMelody/minirag. Two tools: query(question, mode?) — ask and get a cited answer; ingest_text(docId, text, adminKey) — add a document.

The hosted demo endpoint requires basic auth: https://minirag.kimelody.de5.net/sse (ask the owner for credentials).

REST API

Method	Path	Description
POST	`/api/chat`	Ask; returns answer + cited sources (JSON)
POST	`/api/chat/stream`	Same, streamed as SSE (`meta` / `token` / `sources` / `done`)
GET	`/api/search?q=&mode=`	Retrieval debug: `vector` \| `hybrid` \| `rerank`
POST	`/api/documents/text`	Ingest `{docId, text}` (requires `X-Admin-Key`)
POST	`/api/documents`	Ingest an uploaded file, multipart (requires `X-Admin-Key`)

Evaluation

An eval harness ships in eval/: labeled question sets, Top-1 / Recall / MRR scoring over three retrieval modes — hybrid+rerank reaches Top-1 100% / MRR 1.0 on the demo set (report); a 20-question labor-law evaluation with corpus-cleaning scripts lives in eval/law/. Bring your own corpus; raw source texts are not redistributed.

Build from source

Requires Java 21. API keys can be put in a .env file in the working directory (git-ignored).

中文说明

单进程私有化 RAG 知识库：SQLite 存储 + 混合检索（向量 + BM25，RRF 融合，可选 LLM 重排），回答带可点击引用角标，自带网页演示、REST API 与 MCP server（SSE），内存占用约 250MB，1GB 小服务器可跑。在线演示（访问码联系作者）。

License

MIT

Source: README.md at commit 94af130

Tools

This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

v0.1.0LatestOct 15, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts