Smart Connections MCP
S

Smart Connections MCP

This is an MCP server designed for the Smart Connections plugin, providing read-only semantic search functionality for the Obsidian knowledge base, emphasizing security and lightweight implementation.
2 points
0

What is the Smart Connections MCP Server?

This is a bridge connecting Claude Code and the Obsidian knowledge base. It allows you to search your notes using natural language and find relevant content, just like having an intelligent conversation in your knowledge base.

How to use the Smart Connections MCP Server?

After installation and configuration, you can directly ask questions about your notes in Claude Code, and the system will automatically find the most relevant note content. For example, you can ask 'What are the ideas about project management in my notes?'

Applicable scenarios

This tool is especially useful when you need to quickly find specific information in your notes, look for related concepts, or refer to previous thinking records when writing code.

Main features

Text search
Search note content using natural language. The system will automatically understand your query intention and find the most relevant notes.
Semantic search
Find notes based on semantic similarity. Relevant content can be found even without exact keyword matches.
Local inference
All search processing is done locally to protect your privacy without sending data to the cloud.
Read-only access
Safely read note content without modifying or deleting any of your files.
Offline work
You can access and search your notes even when Obsidian is not running.
Advantages
๐Ÿ”’ Security first: Strict path verification and permission control
๐Ÿš€ Fast response: Local processing ensures fast search speed
๐Ÿ›ก๏ธ Privacy protection: All data is processed locally
๐Ÿ“š Intelligent search: Based on semantic understanding rather than simple keyword matching
โšก Lightweight: Minimized dependencies and efficient operation
Limitations
๐Ÿ“ Single knowledge base: Each instance can only connect to one Obsidian knowledge base
๐Ÿ” Dependency on indexing: The Smart Connections plugin is required to pre - build the index
๐Ÿ’พ First download: You need to download a model file of about 50MB for the first use
๐Ÿ“ Read-only access: You cannot edit note content through this tool

How to use

Installation prerequisites
Make sure you have installed Node.js 18+ and the Obsidian and Smart Connections plugins
Download and build
Clone the code repository and install dependencies
Configure Claude Code
Add the server to the Claude Code configuration
Restart and start using
Restart Claude Code, and then you can start searching your notes

Usage examples

Research material organization
When you need to find previously collected research materials, you can use semantic search to quickly locate relevant content
Project document reference
Refer to previous project documents and design ideas when writing new code
Concept association discovery
Discover conceptual connections between different notes and inspire new thinking

Frequently Asked Questions

Do I need to install Obsidian to use this tool?
Will this tool modify my notes?
Why do I need to download the model file for the first use?
Can I connect to multiple Obsidian knowledge bases simultaneously?
How accurate are the search results?

Related resources

Smart Connections plugin
The smart connection plugin for Obsidian, providing semantic search functionality
Model Context Protocol
Official documentation and specifications for MCP
Obsidian official website
The official website of the Obsidian note - taking software
GitHub repository
The source code and latest updates of this project

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "smart-connections": {
      "command": "node",
      "args": ["/path/to/smart-connections-mcp/dist/index.js"],
      "env": {
        "VAULT_PATH": "/path/to/your/obsidian/vault"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
5.9K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
5.5K
4.5 points
H
Haiku.rag
Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.
Python
9.1K
5 points
C
Cipher
Cipher is an open-source memory layer framework designed for programming AI agents. It integrates with various IDEs and AI coding assistants through the MCP protocol, providing core functions such as automatic memory generation, team memory sharing, and dual-system memory management.
TypeScript
0
5 points
A
Apple Notes MCP
A server that provides local Apple Notes database access for the Claude desktop client, supporting reading and searching of note content.
Python
14.6K
4.3 points
M
MCP Server Weread
The WeRead MCP Server is a lightweight service that bridges WeRead data and AI clients, enabling in - depth interaction between reading notes and AI.
TypeScript
15.2K
4 points
M
MCP Notion Server
Certified
The Notion MCP Server is a middleware service that connects the Notion API with the LLM, optimizing interaction efficiency through Markdown conversion.
TypeScript
16.7K
5 points
M
MCP Obsidian
This project is an MCP server used to interact with the Obsidian note application through the Local REST API plugin of Obsidian. It provides various tools to operate and manage files in Obsidian, including listing files, retrieving file content, searching, modifying content, and deleting files.
Python
20.2K
5 points
N
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
20.2K
4.5 points
G
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
24.2K
4.3 points
M
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
35.2K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.3K
4.3 points
U
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#
31.0K
5 points
F
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
64.2K
4.5 points
G
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
21.0K
4.5 points
C
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
97.8K
4.7 points