MiniRAG is answering right now. Last checked 10 min ago. Last commit 28 Oct 2026.
Lightweight self-hosted RAG knowledge base with hybrid retrieval and cited answers.
We read the source, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
d.innerHTML = html.trim();
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.
claude mcp add minirag --transport sse https://minirag.kimelody.de5.net/sse
https://minirag.kimelody.de5.net/sse
[mcp_servers.minirag]
url = "https://minirag.kimelody.de5.net/sse"
{
"mcpServers": {
"minirag": {
"url": "https://minirag.kimelody.de5.net/sse"
}
}
}
{
"servers": {
"minirag": {
"type": "sse",
"url": "https://minirag.kimelody.de5.net/sse"
}
}
}
This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://minirag.kimelody.de5.net/sse | sse | needs auth | 212 ms | 10 min ago |
Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
Permission-aware RAG for agents — ingest docs, hybrid search, cited answers (hosted API).
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
Search IPCC AR6 WG1 and answer with page-level citations, or refuse when unsupported.
Build searchable AI research knowledge bases with hybrid vector search directly in Claude Desktop.
Answers built from our own checks of this server.