Wandering Rag
A CLI tool for retrieving personal data from sources such as Notion and Obsidian, storing it in Qdrant, and providing query services through the MCP server
rating : 2.5 points
downloads : 22
What is Wandering RAG?
Wandering RAG is a tool that helps you quickly find information from your personal notes and documents. It can automatically organize the content from platforms like Notion and Obsidian, allowing you to get answers by asking questions in natural language.How to use Wandering RAG?
Simply install the tool and configure your note paths, and it will automatically index the content. Then you can ask questions directly through the command line or integrate it into applications like Claude Desktop.Use cases
It is especially useful when you need to quickly find information scattered in different notes, such as personal life records like the date of pet adoption or the time of the most recent cat litter change.Main features
Multi - platform supportSupports obtaining data from multiple note platforms such as Notion, Obsidian, and Apple Notes
Local storageUses the Qdrant vector database to store data locally to protect privacy
MCP protocol supportProvides services through the Model Context Protocol and can be integrated with other AI tools
Advantages and limitations
Advantages
Runs completely locally to protect the privacy of personal data
Supports multiple commonly used note platforms
Provides fast and accurate query responses
Can be seamlessly integrated with AI tools such as Claude
Limitations
Requires manual configuration of note paths
The initial indexing may take a long time
The Notion function is currently under development (WIP)
How to use
Install the tool
Use uv pip to install the tool into your Python environment
Start the Qdrant service
Use docker - compose to start the Qdrant vector database service
Configure the environment
Copy .env.example to the .env file and configure your note paths
Index the content
Run the indexing command to organize your note content
Start the MCP service
Run the MCP server so that other applications can query
Usage examples
Query pet informationFind the date of pet adoption and the most recent care records you've recorded
Find meeting recordsQuickly find the key points discussed in a project meeting last week
Frequently Asked Questions
Do I need programming knowledge to use this tool?
Is my data secure?
Why does the Notion function show WIP (under development)?
Related resources
Qdrant official documentation
Documentation for using the Qdrant vector database
MCP protocol description
Technical specifications of the Model Context Protocol
Obsidian official website
Official website of the Obsidian note - taking tool
Featured MCP Services

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
141
4.5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
86
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
830
4.3 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
565
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
282
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points