Quadrant
БесплатноНе проверенEnables document storage and semantic search with geospatial filtering using Qdrant, and coordinate conversion between TLC, Plasma, and addresses.
Описание
Enables document storage and semantic search with geospatial filtering using Qdrant, and coordinate conversion between TLC, Plasma, and addresses.
README
A Model Context Protocol (MCP) server providing coordinate conversion tools and document search with Qdrant vector database, featuring quadrant-based spatial search and filtering.
🚀 Features
- Document Storage: Store and retrieve document chunks with optional geolocation
- Quadrant-Based Search: Search within specific geographic quadrants (NE, NW, SE, SW)
- Location-Based Search: Find documents near specific coordinates
- Hybrid Search: Combine semantic search with geospatial filtering
- Fast Vector Search: Powered by Qdrant's efficient vector similarity search
🚀 Quick Start with UV
1. Install UV (if not already installed)
# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
# Or with pip
pip install uv
2. Setup the Project
# Navigate to your project directory
cd MCP_ADDRESS
# Create a virtual environment and install dependencies
uv venv
uv pip install -e .
3. Run the MCP Server
# Activate the virtual environment (optional, uv can run without activation)
# On macOS/Linux:
source .venv/bin/activate
# On Windows:
.venv\Scripts\activate
# Run
python -m uvicorn main:app --host 0.0.0.0 --port 8000 --reload
The server will start on http://127.0.0.1:8000/sse/
To run the MCP inspector
npx @modelcontextprotocol/inspector http://127.0.0.1:8000/sse/
🔧 Configure Claude Desktop
Add this to your Claude Desktop config file:
Location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Configuration:
{
"mcpServers": {
"quadrant": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/MCP_ADDRESS",
"run",
"python",
"main.py"
]
}
}
}
Replace /absolute/path/to/MCP_QUADRANT with your actual project path.
📦 Available Tools
Coordinate Conversion
- tlc_to_address_tool - Convert TLC codes to addresses
- address_to_tlc_tool - Convert addresses to TLC codes
- address_to_plasma_tool - Convert addresses to Plasma format
- plasma_to_address_tool - Convert Plasma coordinates to addresses
Document Search & Storage
- store_document_chunks - Store document chunks with optional geolocation
- search_documents_by_quadrant - Search within a specific geographic quadrant
- search_documents_near_location - Search near specific coordinates
- search_documents_by_filename - Search documents by filename
Установка Quadrant
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/sakshi-rumsan/mcp_addressFAQ
Quadrant MCP бесплатный?
Да, Quadrant MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Quadrant?
Нет, Quadrant работает без API-ключей и переменных окружения.
Quadrant — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить Quadrant в Claude Desktop, Claude Code или Cursor?
Открой Quadrant на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
GitHub
PRs, issues, code search, CI status
автор: GitHubFilesystem
Secure file operations with configurable access controls.
Memory
Knowledge graph-based persistent memory system.
Template MCP Server
A CLI tool to create a new Model Context Protocol server project with TypeScript support, dual transport options, and an extensible structure
автор: mcpdotdirectCompare Quadrant with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории development
