Is the Kwipu MCP server actively maintained?

The Kwipu MCP server was last committed 2mo ago and has 2 contributors. Issue health: 67% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

Kwipu MCP Server

Name: benmaster82/Kwipu
Rating: 3.8 (1 reviews)
Author: benmaster82

benmaster82/Kwipu

Score: 70.2 Rank #4012 Search & RAG

[![AgentRank](https://agentrank-ai.com/api/v1/badge/benmaster82--Kwipu)](https://agentrank-ai.com/tool/benmaster82--Kwipu/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of benmaster82/Kwipu? Claim this listing →

Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.

Add AgentRank to Claude Code Discover and compare tools like benmaster82/Kwipu — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

benmaster82/Kwipu is a Python tool licensed under MIT. Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama. Topics: llm, md, natural-language, obsidian, ollama, rag, rag-chatbot, terminal-ui, embeddings, llama-index, knowledge-graph, markdown, graph-rag, obsidian-notes, obsidian-vault, offline, offline-first, claude-code, mcp, mcp-tools.

Ranked #4012 out of 24846 indexed tools.

Ecosystem

Python MIT

llmmdnatural-languageobsidianollamaragrag-chatbotterminal-uiembeddingsllama-indexknowledge-graphmarkdowngraph-ragobsidian-notesobsidian-vaultofflineoffline-firstclaude-codemcpmcp-tools

Score Breakdown

Stars 15% 609

609 stars → growing community

Freshness 25% 2mo ago

Last commit 2mo ago → moderate activity

Issue Health 25% 67%

2/3 issues closed → decent issue management

Contributors 10% 2

2 contributors → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 61

Description Detailed

License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Freshness high impact

Last commit was 64 days ago — a recent commit would boost your freshness score

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/benmaster82--Kwipu)](https://agentrank-ai.com/tool/benmaster82--Kwipu/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/benmaster82--Kwipu/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/benmaster82--Kwipu" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="benmaster82/Kwipu"></script>

Details

Stars: 609
Forks: 61
Open Issues: 1
Closed Issues: 2
Contributors: 2
Dependents: —
Language: Python
License: MIT
Last Commit: 2mo ago

Matched Queries

topic:mcp

From the README

<p align="center">
  
</p>

# Kwipu

**English** | [简体中文](README.zh-CN.md) | [Tiếng Việt](README.vi.md)

Kwipu turns a folder of documents into a property-graph RAG index that you can explore and query from an interactive terminal, a 3D web interface, or an MCP client. It works with ordinary knowledge folders and Obsidian-style vaults.

> **About “fully local”:** Kwipu can run fully locally when you select a local Ollama LLM and embedding model. The intentional default LLM is `gpt-oss:20b-cloud`, which can send document chunks, retrieved context, and questions to its provider. [Choose cloud or local before indexing](#choose-cloud-or-local).

## Choose your path

| I want to… | Start here |
|---|---|
| Ask my notes directly in a terminal | [Terminal-only use](#terminal-only-use) |
| Explore the graph and ask from a browser | [Quick start: web UI](#quick-start-web-ui) |
| Use my own notes or Obsidian vault | [Use your own document folder](#use-your-own-document-folder) |
| Connect an AI

Read full README on GitHub →